Dataset Viewer
image_path
stringlengths 42
61
| prompt
stringlengths 18
514
| normalized_bbox
listlengths 4
4
| images
images listlengths 1
1
| easyr1_prompt
stringlengths 275
771
| bbox
listlengths 4
4
| messages
listlengths 3
3
| original_image_width
int64 196
4.03k
| image_width
int64 196
3.08k
| image_height
int64 112
5.35k
|
|---|---|---|---|---|---|---|---|---|---|
autogui-images/autogui_2500717_92944f8f.png
|
<image>
I'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element acts as a navigation link, directing users to the WhatsApp extension page. It provides users with essential information about the extension, such as its name and popularity, through the displayed rating and number of ratings. Interacting with this link enables users to explore the WhatsApp extension in more detail.
|
[
0.504537045955658,
0.5408482551574707,
0.7422659993171692,
0.6171568036079407
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element acts as a navigation link, directing users to the WhatsApp extension page. It provides users with essential information about the extension, such as its name and popularity, through the displayed rating and number of ratings. Interacting with this link enables users to explore the WhatsApp extension in more detail.
|
[
113,
196,
166,
224
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element acts as a navigation link, directing users to the WhatsApp extension page. It provides users with essential information about the extension, such as its name and popularity, through the displayed rating and number of ratings. Interacting with this link enables users to explore the WhatsApp extension in more detail.",
"role": "user"
},
{
"content": "(139,210)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_2340118_3aad9bff.png
|
<image>
For the element I describe in this page capture, can you predict their positions (with point)? This element triggers the display of a login page for accessing a user's CNN account.
|
[
0.9071075320243835,
0.00033320984221063554,
0.9677004218101501,
0.05491878464818001
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
For the element I describe in this page capture, can you predict their positions (with point)? This element triggers the display of a login page for accessing a user's CNN account.
|
[
380,
0,
406,
13
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nFor the element I describe in this page capture, can you predict their positions (with point)? This element triggers the display of a login page for accessing a user's CNN account.",
"role": "user"
},
{
"content": "(393,6)",
"role": "assistant"
}
] | 420 | 420 | 252 |
|
autogui-images/autogui_2452416_248f8049.png
|
<image>
Please use the provided webpage screenshot to locate the element I describe (with point). This element provides access to the main WordPress.org website.
|
[
0.003346791723743081,
0,
0.04827496409416199,
0.08568648993968964
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Please use the provided webpage screenshot to locate the element I describe (with point). This element provides access to the main WordPress.org website.
|
[
2,
0,
36,
35
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nPlease use the provided webpage screenshot to locate the element I describe (with point). This element provides access to the main WordPress.org website.",
"role": "user"
},
{
"content": "(19,17)",
"role": "assistant"
}
] | 756 | 756 | 420 |
|
pc-agent-e-images/data/events/screenshot/f31f_4e45dc19_7.png
|
<image>
Click on Sound settings
|
[
0.3472155034542084,
0.39623624086380005,
0.38795921206474304,
0.4160313010215759
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on Sound settings
|
[
641,
410,
716,
431
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on Sound settings",
"role": "user"
},
{
"content": "(678,420)",
"role": "assistant"
}
] | 1,848 | 1,848 | 1,036 |
|
seeclick-images/9505d3ba2ce9733092ca1e678b84ad0f.png
|
<image>
Click on "Cookie Policy"
|
[
0.2555095851421356,
0.8407283425331116,
0.3160609304904938,
0.8601909875869751
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on "Cookie Policy"
|
[
658,
1224,
814,
1252
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on \"Cookie Policy\"",
"role": "user"
},
{
"content": "(736,1238)",
"role": "assistant"
}
] | 2,576 | 2,576 | 1,456 |
|
pixmo-points-images/pixmo_505752_78445c39.png
|
<image>
Click on title of page
|
[
0.01507621444761753,
0.014562779106199741,
0.23724482953548431,
0.04912717640399933
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on title of page
|
[
5,
8,
86,
27
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on title of page",
"role": "user"
},
{
"content": "(45,17)",
"role": "assistant"
}
] | 364 | 364 | 560 |
|
autogui-images/autogui_2181883_7b6995b3.png
|
<image>
On this webpage capture, I'll point out a specific element for you to locate (with point). This element provides access to popular content within the community.
|
[
0.01795428805053234,
0.1570984423160553,
0.18968184292316437,
0.21228714287281036
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
On this webpage capture, I'll point out a specific element for you to locate (with point). This element provides access to popular content within the community.
|
[
9,
43,
95,
59
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nOn this webpage capture, I'll point out a specific element for you to locate (with point). This element provides access to popular content within the community.",
"role": "user"
},
{
"content": "(52,51)",
"role": "assistant"
}
] | 504 | 504 | 280 |
|
autogui-images/autogui_2281208_4e6c0702.png
|
<image>
In this webpage capture, I will describe a certain element. Please locate it for me (with point). This element serves as a navigation link, allowing users to access content related to the company's customers on the website. Interacting with this link will likely take the user to a page dedicated to customer-focused information.
|
[
0.5262057781219482,
0.6958786845207214,
0.6889923810958862,
0.7181732058525085
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In this webpage capture, I will describe a certain element. Please locate it for me (with point). This element serves as a navigation link, allowing users to access content related to the company's customers on the website. Interacting with this link will likely take the user to a page dedicated to customer-focused information.
|
[
117,
253,
154,
261
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn this webpage capture, I will describe a certain element. Please locate it for me (with point). This element serves as a navigation link, allowing users to access content related to the company's customers on the website. Interacting with this link will likely take the user to a page dedicated to customer-focused information.",
"role": "user"
},
{
"content": "(135,257)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
pc-agent-e-images/data/events/screenshot/312a_f8d0c259_1.png
|
<image>
Click the three-dot menu
|
[
0.974396288394928,
0.004491664934903383,
0.9960210919380188,
0.04060816392302513
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click the three-dot menu
|
[
1064,
2,
1087,
25
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick the three-dot menu",
"role": "user"
},
{
"content": "(1075,13)",
"role": "assistant"
}
] | 1,092 | 1,092 | 616 |
|
autogui-images/autogui_1011687_5141c172.png
|
<image>
In the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element serves as a mobile navigation toggle, allowing users to expand or collapse the navigation menu for easier browsing on smaller devices.
|
[
0.829104483127594,
0.021851330995559692,
0.9045238494873047,
0.06652263551950455
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element serves as a mobile navigation toggle, allowing users to expand or collapse the navigation menu for easier browsing on smaller devices.
|
[
185,
7,
202,
24
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element serves as a mobile navigation toggle, allowing users to expand or collapse the navigation menu for easier browsing on smaller devices.",
"role": "user"
},
{
"content": "(193,15)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_810960_fff461bc.png
|
<image>
Using the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element serves as a navigation tool, directing users to the main page of the Kaspersky official blog, where they can access a variety of content related to cybersecurity.
|
[
0.10474292188882828,
0.0008118808618746698,
0.616531252861023,
0.06697764992713928
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element serves as a navigation tool, directing users to the main page of the Kaspersky official blog, where they can access a variety of content related to cybersecurity.
|
[
23,
0,
138,
24
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element serves as a navigation tool, directing users to the main page of the Kaspersky official blog, where they can access a variety of content related to cybersecurity.",
"role": "user"
},
{
"content": "(80,12)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_2261475_a1eeb891.png
|
<image>
Based on the screenshot of the page, I give a text description and you give its corresponding location (with point). This element provides direct access to the chat functionality, allowing users to interact with their friends and contacts.
|
[
0.502377986907959,
0.011699086986482143,
0.545474112033844,
0.09584604948759079
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Based on the screenshot of the page, I give a text description and you give its corresponding location (with point). This element provides direct access to the chat functionality, allowing users to interact with their friends and contacts.
|
[
393,
5,
427,
42
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nBased on the screenshot of the page, I give a text description and you give its corresponding location (with point). This element provides direct access to the chat functionality, allowing users to interact with their friends and contacts.",
"role": "user"
},
{
"content": "(410,23)",
"role": "assistant"
}
] | 784 | 784 | 448 |
|
autogui-images/autogui_331535_49f6a626.png
|
<image>
In this web page capture, please predict the positions of the element I describe (with point). This element facilitates the comparison of the product with similar items, either on the same webpage or across multiple pages, providing users with an opportunity to make informed decisions based on the product's features, specifications, and other factors.
|
[
0.7957807183265686,
0.5746304988861084,
1,
0.6438056230545044
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In this web page capture, please predict the positions of the element I describe (with point). This element facilitates the comparison of the product with similar items, either on the same webpage or across multiple pages, providing users with an opportunity to make informed decisions based on the product's features, specifications, and other factors.
|
[
178,
209,
224,
234
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn this web page capture, please predict the positions of the element I describe (with point). This element facilitates the comparison of the product with similar items, either on the same webpage or across multiple pages, providing users with an opportunity to make informed decisions based on the product's features, specifications, and other factors.",
"role": "user"
},
{
"content": "(201,221)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_820883_b2e6b20b.png
|
<image>
Using the provided screenshot, I'll describe a webpage element for you to locate (with point). This element triggers the display of a navigation menu, providing users with quick access to multiple sections of the website.
|
[
0.8769674897193909,
0.017867328599095345,
0.9694432020187378,
0.07138470560312271
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using the provided screenshot, I'll describe a webpage element for you to locate (with point). This element triggers the display of a navigation menu, providing users with quick access to multiple sections of the website.
|
[
196,
6,
217,
25
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing the provided screenshot, I'll describe a webpage element for you to locate (with point). This element triggers the display of a navigation menu, providing users with quick access to multiple sections of the website.",
"role": "user"
},
{
"content": "(206,15)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
pixmo-points-images/pixmo_1203764_2d929c83.png
|
<image>
Click on apply coupon box
|
[
0.32999855279922485,
0.4227118492126465,
0.45881417393684387,
0.48483067750930786
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on apply coupon box
|
[
184,
153,
256,
176
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on apply coupon box",
"role": "user"
},
{
"content": "(220,164)",
"role": "assistant"
}
] | 560 | 560 | 364 |
|
autogui-images/autogui_2501636_fc78f43a.png
|
<image>
Using the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element serves as a navigation point, directing users to news or updates related to WordPress when clicked, enhancing their understanding of the platform and its community.
|
[
0.016976164653897285,
0.248493492603302,
0.1776140034198761,
0.30699849128723145
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element serves as a navigation point, directing users to news or updates related to WordPress when clicked, enhancing their understanding of the platform and its community.
|
[
3,
90,
39,
111
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element serves as a navigation point, directing users to news or updates related to WordPress when clicked, enhancing their understanding of the platform and its community.",
"role": "user"
},
{
"content": "(21,100)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_1762504_8737272a.png
|
<image>
I'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element serves as a navigational tool for users who prefer the Chinese language. Interacting with this link will lead users to the Chinese-language version of the Wiktionary project.
|
[
0.7481910586357117,
0.6587129235267639,
0.7830663919448853,
0.6878176331520081
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element serves as a navigational tool for users who prefer the Chinese language. Interacting with this link will lead users to the Chinese-language version of the Wiktionary project.
|
[
481,
239,
504,
250
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element serves as a navigational tool for users who prefer the Chinese language. Interacting with this link will lead users to the Chinese-language version of the Wiktionary project.",
"role": "user"
},
{
"content": "(492,244)",
"role": "assistant"
}
] | 644 | 644 | 364 |
|
autogui-images/autogui_421327_e86a0ea0.png
|
<image>
In the image above, I will give a series of descriptions of the element to be clicked. Please predict where you want to click (with point). This element triggers a time input interface for changing the alarm time to a specific hour, which initially is set to 9:00 AM.
|
[
0.19671589136123657,
0.22859784960746765,
0.27772650122642517,
0.29262450337409973
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In the image above, I will give a series of descriptions of the element to be clicked. Please predict where you want to click (with point). This element triggers a time input interface for changing the alarm time to a specific hour, which initially is set to 9:00 AM.
|
[
49,
102,
69,
131
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn the image above, I will give a series of descriptions of the element to be clicked. Please predict where you want to click (with point). This element triggers a time input interface for changing the alarm time to a specific hour, which initially is set to 9:00 AM.",
"role": "user"
},
{
"content": "(59,116)",
"role": "assistant"
}
] | 252 | 252 | 448 |
|
autogui-images/autogui_1221699_9ae284f2.png
|
<image>
I'll give textual clues about an element in this webpage screenshot; identify their coordinates (with point). This element acts as a homepage navigation link, enabling users to quickly return to the main content of the webpage.
|
[
0.01636168174445629,
0.3955783247947693,
0.09454650431871414,
0.41699278354644775
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll give textual clues about an element in this webpage screenshot; identify their coordinates (with point). This element acts as a homepage navigation link, enabling users to quickly return to the main content of the webpage.
|
[
3,
143,
21,
151
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll give textual clues about an element in this webpage screenshot; identify their coordinates (with point). This element acts as a homepage navigation link, enabling users to quickly return to the main content of the webpage.",
"role": "user"
},
{
"content": "(12,147)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_622219_dc148c8d.png
|
<image>
From this webpage image, I will describe a specific element. Please predict their exact locations (with point). This element provides access to festival-related content or events.
|
[
0.3013181686401367,
0,
0.3697890341281891,
0.057591281831264496
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
From this webpage image, I will describe a specific element. Please predict their exact locations (with point). This element provides access to festival-related content or events.
|
[
143,
0,
176,
16
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nFrom this webpage image, I will describe a specific element. Please predict their exact locations (with point). This element provides access to festival-related content or events.",
"role": "user"
},
{
"content": "(159,8)",
"role": "assistant"
}
] | 476 | 476 | 280 |
|
autogui-images/autogui_1541962_926eb161.png
|
<image>
I will give textual descriptions of a certain element in the screenshot. Please predict the location of the corresponding element (with point). This element serves as a navigation link for users who already have a WordPress.org account, allowing them to proceed to the login page rather than creating a new account.
|
[
0.3913615047931671,
0.9368544816970825,
0.5106136798858643,
0.9707532525062561
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I will give textual descriptions of a certain element in the screenshot. Please predict the location of the corresponding element (with point). This element serves as a navigation link for users who already have a WordPress.org account, allowing them to proceed to the login page rather than creating a new account.
|
[
219,
288,
285,
298
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI will give textual descriptions of a certain element in the screenshot. Please predict the location of the corresponding element (with point). This element serves as a navigation link for users who already have a WordPress.org account, allowing them to proceed to the login page rather than creating a new account.",
"role": "user"
},
{
"content": "(252,293)",
"role": "assistant"
}
] | 560 | 560 | 308 |
|
autogui-images/autogui_811254_5f6220aa.png
|
<image>
I will describe features on this webpage screenshot; please predict their positions (with point). This element opens the Gmail app, dismissing the original app list view and displaying a Gmail welcome tour.
|
[
0.7865652441978455,
0.4716379940509796,
0.9666023254394531,
0.5803197622299194
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I will describe features on this webpage screenshot; please predict their positions (with point). This element opens the Gmail app, dismissing the original app list view and displaying a Gmail welcome tour.
|
[
176,
237,
216,
292
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI will describe features on this webpage screenshot; please predict their positions (with point). This element opens the Gmail app, dismissing the original app list view and displaying a Gmail welcome tour.",
"role": "user"
},
{
"content": "(196,264)",
"role": "assistant"
}
] | 224 | 224 | 504 |
|
pixmo-points-images/pixmo_1822373_7bbce4d6.png
|
<image>
Click on rectangle
|
[
0.32115447521209717,
0.5909188985824585,
0.6525067687034607,
0.6689868569374084
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on rectangle
|
[
395,
628,
803,
711
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on rectangle",
"role": "user"
},
{
"content": "(599,669)",
"role": "assistant"
}
] | 1,232 | 1,232 | 1,064 |
|
pixmo-points-images/pixmo_020618_d9d0797c.png
|
<image>
Click on Pixelated car graphic
|
[
0.7611970901489258,
0.09769263863563538,
0.8136059045791626,
0.19243647158145905
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on Pixelated car graphic
|
[
724,
65,
774,
129
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on Pixelated car graphic",
"role": "user"
},
{
"content": "(749,97)",
"role": "assistant"
}
] | 952 | 952 | 672 |
|
autogui-images/autogui_1061710_da2e2192.png
|
<image>
I'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element triggers the display of search results as files within the search interface.
|
[
0.03769632428884506,
0.13546352088451385,
0.06224435195326805,
0.16061526536941528
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element triggers the display of search results as files within the search interface.
|
[
25,
49,
41,
58
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element triggers the display of search results as files within the search interface.",
"role": "user"
},
{
"content": "(33,53)",
"role": "assistant"
}
] | 672 | 672 | 364 |
|
autogui-images/autogui_1180618_5be9464e.png
|
<image>
Please determine the location of the element I describe in this webpage screenshot (with point). This element serves as a gateway to the Chinese version of the website, allowing users who prefer simplified Chinese to access the content in their preferred language.
|
[
0.7187512516975403,
0.0005162835004739463,
0.974302351474762,
0.06423845142126083
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Please determine the location of the element I describe in this webpage screenshot (with point). This element serves as a gateway to the Chinese version of the website, allowing users who prefer simplified Chinese to access the content in their preferred language.
|
[
161,
0,
218,
23
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nPlease determine the location of the element I describe in this webpage screenshot (with point). This element serves as a gateway to the Chinese version of the website, allowing users who prefer simplified Chinese to access the content in their preferred language.",
"role": "user"
},
{
"content": "(189,11)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_1730904_7cb95bd0.png
|
<image>
I will give textual descriptions of a certain element in the screenshot. Please predict the location of the corresponding element (with point). This element toggles a concise chat mode, allowing users to engage in fact-finding conversations with the AI assistant.
|
[
0.6173804998397827,
0.6459594964981079,
0.8181673884391785,
0.7169318795204163
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I will give textual descriptions of a certain element in the screenshot. Please predict the location of the corresponding element (with point). This element toggles a concise chat mode, allowing users to engage in fact-finding conversations with the AI assistant.
|
[
138,
235,
183,
260
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI will give textual descriptions of a certain element in the screenshot. Please predict the location of the corresponding element (with point). This element toggles a concise chat mode, allowing users to engage in fact-finding conversations with the AI assistant.",
"role": "user"
},
{
"content": "(160,247)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
seeclick-images/2a21860f8a36d8ebbed406d3aabc8690.png
|
<image>
Click on "Over ons"
|
[
0.5196879506111145,
0.0577717050909996,
0.5675439834594727,
0.10181516408920288
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on "Over ons"
|
[
1251,
77,
1366,
136
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on \"Over ons\"",
"role": "user"
},
{
"content": "(1308,106)",
"role": "assistant"
}
] | 2,408 | 2,408 | 1,344 |
|
autogui-images/autogui_1331686_09da47f1.png
|
<image>
Using this webpage screenshot, I'll describe an element. Please locate it (with point). This element is a navigation link that provides users with access to more information about the W3C's work related to security. Interacting with this link would allow users to read detailed content about the W3C's efforts and guidelines regarding web security.
|
[
0.3601841330528259,
0.50240159034729,
0.5748454928398132,
0.5504119992256165
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using this webpage screenshot, I'll describe an element. Please locate it (with point). This element is a navigation link that provides users with access to more information about the W3C's work related to security. Interacting with this link would allow users to read detailed content about the W3C's efforts and guidelines regarding web security.
|
[
80,
182,
128,
200
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing this webpage screenshot, I'll describe an element. Please locate it (with point). This element is a navigation link that provides users with access to more information about the W3C's work related to security. Interacting with this link would allow users to read detailed content about the W3C's efforts and guidelines regarding web security.",
"role": "user"
},
{
"content": "(104,191)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_800323_c2d1bb9d.png
|
<image>
In the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element triggers a change in the displayed content on the webpage to a category related to music. Interacting with it allows users to explore various content related to music, such as videos, playlists, or channels.
|
[
0.4932112395763397,
0.093134306371212,
0.5463047623634338,
0.142330139875412
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element triggers a change in the displayed content on the webpage to a category related to music. Interacting with it allows users to explore various content related to music, such as videos, playlists, or channels.
|
[
290,
31,
321,
47
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element triggers a change in the displayed content on the webpage to a category related to music. Interacting with it allows users to explore various content related to music, such as videos, playlists, or channels.",
"role": "user"
},
{
"content": "(305,39)",
"role": "assistant"
}
] | 588 | 588 | 336 |
|
pixmo-points-images/pixmo_1369035_64febcd8.png
|
<image>
Click on Website link
|
[
0.7578328847885132,
0.5143507719039917,
0.830464243888855,
0.5942037105560303
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on Website link
|
[
445,
273,
488,
316
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on Website link",
"role": "user"
},
{
"content": "(466,294)",
"role": "assistant"
}
] | 588 | 588 | 532 |
|
autogui-images/autogui_2322003_d5010276.png
|
<image>
In this web page image, please locate the element as I describe it (with point). This element provides a free trial option for users to experience Adobe's products or services before committing to a purchase.
|
[
0.8536543846130371,
0.016786476597189903,
0.919366717338562,
0.0699462816119194
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In this web page image, please locate the element as I describe it (with point). This element provides a free trial option for users to experience Adobe's products or services before committing to a purchase.
|
[
740,
7,
798,
33
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn this web page image, please locate the element as I describe it (with point). This element provides a free trial option for users to experience Adobe's products or services before committing to a purchase.",
"role": "user"
},
{
"content": "(769,20)",
"role": "assistant"
}
] | 868 | 868 | 476 |
|
pc-agent-e-images/data/events/screenshot/1a3b_8bea31b7_13.png
|
<image>
Click Google Chrome to set as default PDF app
|
[
0.36398792266845703,
0.3754159212112427,
0.6385614275932312,
0.4365479350090027
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click Google Chrome to set as default PDF app
|
[
305,
178,
536,
207
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick Google Chrome to set as default PDF app",
"role": "user"
},
{
"content": "(420,192)",
"role": "assistant"
}
] | 840 | 840 | 476 |
|
autogui-images/autogui_2280186_a27efc86.png
|
<image>
I will describe an element from a webpage screenshot; your role is to locate it (with point). This element navigates to the next instructional page on Google Calendar guidance.
|
[
0.9031976461410522,
0.8911444544792175,
0.9719424843788147,
0.9305973649024963
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I will describe an element from a webpage screenshot; your role is to locate it (with point). This element navigates to the next instructional page on Google Calendar guidance.
|
[
202,
424,
217,
442
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI will describe an element from a webpage screenshot; your role is to locate it (with point). This element navigates to the next instructional page on Google Calendar guidance.",
"role": "user"
},
{
"content": "(209,433)",
"role": "assistant"
}
] | 224 | 224 | 476 |
|
autogui-images/autogui_1861237_f35e7e5d.png
|
<image>
From the given webpage screenshot, I need you to identify the locations of the described element (with point). This element redirects users to a community-focused blog post listing, allowing them to access and explore relevant articles related to the Answer project's community.
|
[
0.15689893066883087,
0.1513858586549759,
0.3639659285545349,
0.17367039620876312
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
From the given webpage screenshot, I need you to identify the locations of the described element (with point). This element redirects users to a community-focused blog post listing, allowing them to access and explore relevant articles related to the Answer project's community.
|
[
35,
55,
81,
63
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nFrom the given webpage screenshot, I need you to identify the locations of the described element (with point). This element redirects users to a community-focused blog post listing, allowing them to access and explore relevant articles related to the Answer project's community.",
"role": "user"
},
{
"content": "(58,59)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_401001_c2d7d4b4.png
|
<image>
Please use the provided webpage screenshot to locate the element I describe (with point). This element allows users to choose their preferred language for the AWS Console signup process, offering a more user-friendly and inclusive experience for users who speak different languages.
|
[
0.747963011264801,
0.008699441328644753,
0.9790071845054626,
0.09506243467330933
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Please use the provided webpage screenshot to locate the element I describe (with point). This element allows users to choose their preferred language for the AWS Console signup process, offering a more user-friendly and inclusive experience for users who speak different languages.
|
[
167,
3,
219,
34
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nPlease use the provided webpage screenshot to locate the element I describe (with point). This element allows users to choose their preferred language for the AWS Console signup process, offering a more user-friendly and inclusive experience for users who speak different languages.",
"role": "user"
},
{
"content": "(193,18)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
pixmo-points-images/pixmo_558428_584af363.png
|
<image>
Click on Marijuana leaves
|
[
0.09117774665355682,
0.23296894133090973,
0.8342834115028381,
0.7691622972488403
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on Marijuana leaves
|
[
56,
78,
513,
258
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on Marijuana leaves",
"role": "user"
},
{
"content": "(284,168)",
"role": "assistant"
}
] | 616 | 616 | 336 |
|
autogui-images/autogui_2650474_e37a4bfd.png
|
<image>
I'll give descriptions of a certain webpage element; please identify where they are in this screenshot (with point). This element launches the phone dialer application.
|
[
0.057983748614788055,
0.7631481885910034,
0.19872431457042694,
0.8317700028419495
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll give descriptions of a certain webpage element; please identify where they are in this screenshot (with point). This element launches the phone dialer application.
|
[
12,
363,
44,
395
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll give descriptions of a certain webpage element; please identify where they are in this screenshot (with point). This element launches the phone dialer application.",
"role": "user"
},
{
"content": "(28,379)",
"role": "assistant"
}
] | 224 | 224 | 476 |
|
autogui-images/autogui_021927_053c3187.png
|
<image>
In this web page capture, please predict the positions of the element I describe (with point). This element serves as a navigational aid, directing users to the PayPal main website where they can proceed with changing their password as instructed in the provided steps.
|
[
0.030234666541218758,
0.7324725389480591,
0.8424229025840759,
0.9885594844818115
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In this web page capture, please predict the positions of the element I describe (with point). This element serves as a navigational aid, directing users to the PayPal main website where they can proceed with changing their password as instructed in the provided steps.
|
[
6,
266,
188,
359
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn this web page capture, please predict the positions of the element I describe (with point). This element serves as a navigational aid, directing users to the PayPal main website where they can proceed with changing their password as instructed in the provided steps.",
"role": "user"
},
{
"content": "(97,312)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_880631_324b0e4e.png
|
<image>
Using this webpage screenshot, I'll describe an element. Please locate it (with point). This element initiates the sign-in process and prompts the application to authenticate the user, temporarily replacing the original sign-in screen with a progress status view.
|
[
0.8753190636634827,
0.899581789970398,
0.9784564971923828,
0.9899433851242065
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using this webpage screenshot, I'll describe an element. Please locate it (with point). This element initiates the sign-in process and prompts the application to authenticate the user, temporarily replacing the original sign-in screen with a progress status view.
|
[
392,
226,
438,
249
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing this webpage screenshot, I'll describe an element. Please locate it (with point). This element initiates the sign-in process and prompts the application to authenticate the user, temporarily replacing the original sign-in screen with a progress status view.",
"role": "user"
},
{
"content": "(415,237)",
"role": "assistant"
}
] | 448 | 448 | 252 |
|
pc-agent-e-images/data/events/screenshot/e54a_31bc2f00_4.png
|
<image>
Select the circle shape tool
|
[
0.3136010766029358,
0.11560805886983871,
0.32944902777671814,
0.17141151428222656
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select the circle shape tool
|
[
500,
103,
525,
153
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect the circle shape tool",
"role": "user"
},
{
"content": "(512,128)",
"role": "assistant"
}
] | 1,596 | 1,596 | 896 |
|
pixmo-points-images/pixmo_325279_5627c5f9.jpg
|
<image>
Click on Green checkmark
|
[
0.7061190605163574,
0.7795192003250122,
0.7480029463768005,
0.8522992730140686
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on Green checkmark
|
[
909,
567,
963,
620
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on Green checkmark",
"role": "user"
},
{
"content": "(936,593)",
"role": "assistant"
}
] | 1,288 | 1,288 | 728 |
|
pixmo-points-images/pixmo_689032_e5b9a87d.jpg
|
<image>
Click on Award
|
[
0.7809963226318359,
0.9224748611450195,
1,
1
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on Award
|
[
524,
878,
672,
952
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on Award",
"role": "user"
},
{
"content": "(598,915)",
"role": "assistant"
}
] | 672 | 672 | 952 |
|
autogui-images/autogui_1161451_8d0ba7a9.png
|
<image>
From this webpage image, I will describe a specific element. Please predict their exact locations (with point). This element triggers the display of a list of Microsoft's products and services when interacted with, providing users with a comprehensive overview of the various offerings from Microsoft.
|
[
0.017697656527161598,
0.01494371797889471,
0.0974428802728653,
0.06373555958271027
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
From this webpage image, I will describe a specific element. Please predict their exact locations (with point). This element triggers the display of a list of Microsoft's products and services when interacted with, providing users with a comprehensive overview of the various offerings from Microsoft.
|
[
3,
5,
21,
23
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nFrom this webpage image, I will describe a specific element. Please predict their exact locations (with point). This element triggers the display of a list of Microsoft's products and services when interacted with, providing users with a comprehensive overview of the various offerings from Microsoft.",
"role": "user"
},
{
"content": "(12,14)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
seeclick-images/18668db21c0e57ca43bb3bcf06d60a24.png
|
<image>
Click on "omega"
|
[
0.40589186549186707,
0.33228862285614014,
0.5854960083961487,
0.4230248034000397
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on "omega"
|
[
772,
353,
1114,
450
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on \"omega\"",
"role": "user"
},
{
"content": "(943,401)",
"role": "assistant"
}
] | 1,904 | 1,904 | 1,064 |
|
autogui-images/autogui_300209_25774886.png
|
<image>
With this screenshot of a webpage, can you locate the element I describe (with point)? This element triggers a navigation to the shopping cart or wish list, providing users with easy access to their selected items and allowing them to continue their shopping experience.
|
[
0.7824105024337769,
0.006112921517342329,
0.878959059715271,
0.06017652899026871
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
With this screenshot of a webpage, can you locate the element I describe (with point)? This element triggers a navigation to the shopping cart or wish list, providing users with easy access to their selected items and allowing them to continue their shopping experience.
|
[
175,
2,
196,
21
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nWith this screenshot of a webpage, can you locate the element I describe (with point)? This element triggers a navigation to the shopping cart or wish list, providing users with easy access to their selected items and allowing them to continue their shopping experience.",
"role": "user"
},
{
"content": "(185,11)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
pixmo-points-images/pixmo_1624139_7d7cb093.png
|
<image>
Click on Australia flag
|
[
0.38944944739341736,
0.3252719044685364,
0.42389026284217834,
0.37540483474731445
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on Australia flag
|
[
327,
163,
356,
189
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on Australia flag",
"role": "user"
},
{
"content": "(341,176)",
"role": "assistant"
}
] | 840 | 840 | 504 |
|
autogui-images/autogui_090394_41d83bf7.png
|
<image>
In the provided web page image, I'll describe a specific element. Identify their locations, please (with point). This element serves as a navigational aid, providing users with a direct link to the 'GratefulDead' forum, making it easier for users to access related discussions or information within the Internet Archive Forums.
|
[
0.31188005208969116,
0.2660958468914032,
0.570960521697998,
0.29193735122680664
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In the provided web page image, I'll describe a specific element. Identify their locations, please (with point). This element serves as a navigational aid, providing users with a direct link to the 'GratefulDead' forum, making it easier for users to access related discussions or information within the Internet Archive Forums.
|
[
69,
96,
127,
106
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn the provided web page image, I'll describe a specific element. Identify their locations, please (with point). This element serves as a navigational aid, providing users with a direct link to the 'GratefulDead' forum, making it easier for users to access related discussions or information within the Internet Archive Forums.",
"role": "user"
},
{
"content": "(98,101)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_1550085_7e4dc26d.png
|
<image>
Using this webpage screenshot, I'll describe an element. Please locate it (with point). This element serves as a navigation tool, directing users to the homepage of the FT Chinese website, providing easy access to the main content of the webpage.
|
[
0.3646429479122162,
0.006845671217888594,
0.6284136772155762,
0.059865761548280716
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using this webpage screenshot, I'll describe an element. Please locate it (with point). This element serves as a navigation tool, directing users to the homepage of the FT Chinese website, providing easy access to the main content of the webpage.
|
[
81,
2,
140,
21
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing this webpage screenshot, I'll describe an element. Please locate it (with point). This element serves as a navigation tool, directing users to the homepage of the FT Chinese website, providing easy access to the main content of the webpage.",
"role": "user"
},
{
"content": "(110,11)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_2462259_ceda7dd8.png
|
<image>
For the element I describe in this page capture, can you predict their positions (with point)? This element serves as a user interface control to accept the use of cookies and close the related notification on the website, enhancing user experience by giving them the option to manage their cookie preferences.
|
[
0.4825197756290436,
0.9407662153244019,
0.6165875792503357,
0.9630405902862549
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
For the element I describe in this page capture, can you predict their positions (with point)? This element serves as a user interface control to accept the use of cookies and close the related notification on the website, enhancing user experience by giving them the option to manage their cookie preferences.
|
[
108,
342,
138,
350
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nFor the element I describe in this page capture, can you predict their positions (with point)? This element serves as a user interface control to accept the use of cookies and close the related notification on the website, enhancing user experience by giving them the option to manage their cookie preferences.",
"role": "user"
},
{
"content": "(123,346)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_2290507_a10effde.png
|
<image>
I'll describe certain an element on this webpage image; your task is to find their locations (with point). This element redirects the user to the Microsoft homepage, allowing them to explore and discover new products, access their account, and search for specific content.
|
[
0.34119537472724915,
0.0014115810627117753,
0.653133749961853,
0.06122327223420143
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll describe certain an element on this webpage image; your task is to find their locations (with point). This element redirects the user to the Microsoft homepage, allowing them to explore and discover new products, access their account, and search for specific content.
|
[
76,
0,
146,
22
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll describe certain an element on this webpage image; your task is to find their locations (with point). This element redirects the user to the Microsoft homepage, allowing them to explore and discover new products, access their account, and search for specific content.",
"role": "user"
},
{
"content": "(111,11)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_1051935_b9f8574f.png
|
<image>
I'll give descriptions of a certain webpage element; please identify where they are in this screenshot (with point). This element provides further troubleshooting guidance for users encountering errors during login.
|
[
0.010267066769301891,
0.17006021738052368,
0.6738319993019104,
0.46502214670181274
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll give descriptions of a certain webpage element; please identify where they are in this screenshot (with point). This element provides further troubleshooting guidance for users encountering errors during login.
|
[
4,
42,
301,
117
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll give descriptions of a certain webpage element; please identify where they are in this screenshot (with point). This element provides further troubleshooting guidance for users encountering errors during login.",
"role": "user"
},
{
"content": "(152,79)",
"role": "assistant"
}
] | 448 | 448 | 252 |
|
autogui-images/autogui_941610_09d1a86c.png
|
<image>
Given a screenshot, I will describe a specific element; your task is to predict their locations (with point). This element provides information about the authorship and revision history of the code.
|
[
0.8874232769012451,
0.18269072473049164,
0.9370974898338318,
0.22159910202026367
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Given a screenshot, I will describe a specific element; your task is to predict their locations (with point). This element provides information about the authorship and revision history of the code.
|
[
844,
97,
892,
117
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nGiven a screenshot, I will describe a specific element; your task is to predict their locations (with point). This element provides information about the authorship and revision history of the code.",
"role": "user"
},
{
"content": "(868,107)",
"role": "assistant"
}
] | 952 | 952 | 532 |
|
pc-agent-e-images/data/events/screenshot/b102_a705e46e_17.png
|
<image>
Select "Los Angeles, CA" from search results
|
[
0.31855207681655884,
0.39524614810943604,
0.4092716872692108,
0.43113383650779724
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select "Los Angeles, CA" from search results
|
[
553,
387,
710,
422
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect \"Los Angeles, CA\" from search results",
"role": "user"
},
{
"content": "(631,404)",
"role": "assistant"
}
] | 1,736 | 1,736 | 980 |
|
autogui-images/autogui_2251641_46d1ff0b.png
|
<image>
Using the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element provides access to additional information or resources related to a specific topic or service.
|
[
0.5080485939979553,
0.2896960377693176,
0.56756991147995,
0.3256916105747223
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element provides access to additional information or resources related to a specific topic or service.
|
[
440,
137,
492,
155
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element provides access to additional information or resources related to a specific topic or service.",
"role": "user"
},
{
"content": "(466,146)",
"role": "assistant"
}
] | 868 | 868 | 476 |
|
pc-agent-e-images/data/events/screenshot/d41a_93cd75dd_7.png
|
<image>
Click the Sepia checkbox
|
[
0.18221431970596313,
0.34732550382614136,
0.2582719027996063,
0.37307313084602356
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click the Sepia checkbox
|
[
316,
340,
448,
365
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick the Sepia checkbox",
"role": "user"
},
{
"content": "(382,352)",
"role": "assistant"
}
] | 1,736 | 1,736 | 980 |
|
pixmo-points-images/pixmo_1314181_5886acf4.png
|
<image>
Click on task starting 13 june
|
[
0.8165425062179565,
0.9450491070747375,
0.9180724024772644,
0.9795053601264954
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on task starting 13 june
|
[
571,
423,
642,
438
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on task starting 13 june",
"role": "user"
},
{
"content": "(606,430)",
"role": "assistant"
}
] | 700 | 700 | 448 |
|
autogui-images/autogui_2261537_efb88fa5.png
|
<image>
In this web page capture, please predict the positions of the element I describe (with point). This element triggers a navigation to the section of the repository, providing users with a way to view, create, or manage issues related to the project.
|
[
0.22302280366420746,
0.17250220477581024,
0.4334735870361328,
0.23709292709827423
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In this web page capture, please predict the positions of the element I describe (with point). This element triggers a navigation to the section of the repository, providing users with a way to view, create, or manage issues related to the project.
|
[
49,
62,
97,
86
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn this web page capture, please predict the positions of the element I describe (with point). This element triggers a navigation to the section of the repository, providing users with a way to view, create, or manage issues related to the project.",
"role": "user"
},
{
"content": "(73,74)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_1081707_4bd4c3a5.png
|
<image>
Given this screenshot of a webpage, I'll describe an element; locate it for me (with point). This element triggers the display of a list of Microsoft products and services when interacted with, providing users with a comprehensive view of the various offerings available from Microsoft.
|
[
0.012720796279609203,
0.009335505776107311,
0.10083644837141037,
0.07403162866830826
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Given this screenshot of a webpage, I'll describe an element; locate it for me (with point). This element triggers the display of a list of Microsoft products and services when interacted with, providing users with a comprehensive view of the various offerings available from Microsoft.
|
[
2,
3,
22,
26
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nGiven this screenshot of a webpage, I'll describe an element; locate it for me (with point). This element triggers the display of a list of Microsoft products and services when interacted with, providing users with a comprehensive view of the various offerings available from Microsoft.",
"role": "user"
},
{
"content": "(12,14)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_2042136_2eef7520.png
|
<image>
Using the screenshot of this webpage, identify the coordinates of the element I describe (with point). This element triggers the expansion of a submenu containing various options related to the community aspect of the platform, allowing users to access community-related resources more easily.
|
[
0.04858211800456047,
0.9574248194694519,
0.2889338433742523,
0.9847179651260376
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using the screenshot of this webpage, identify the coordinates of the element I describe (with point). This element triggers the expansion of a submenu containing various options related to the community aspect of the platform, allowing users to access community-related resources more easily.
|
[
10,
348,
64,
358
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing the screenshot of this webpage, identify the coordinates of the element I describe (with point). This element triggers the expansion of a submenu containing various options related to the community aspect of the platform, allowing users to access community-related resources more easily.",
"role": "user"
},
{
"content": "(37,353)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_1042529_73ad56cc.png
|
<image>
Using the attached screenshot of a webpage, please find the coordinates of the described element (with point). This element provides users with information about financing options or incentives related to the purchase of the iPhone 15 Pro. Interacting with this link likely leads to further details about financing options or special promotions for the product.
|
[
0.054671477526426315,
0.3324267566204071,
0.4426967203617096,
0.39575397968292236
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using the attached screenshot of a webpage, please find the coordinates of the described element (with point). This element provides users with information about financing options or incentives related to the purchase of the iPhone 15 Pro. Interacting with this link likely leads to further details about financing options or special promotions for the product.
|
[
12,
121,
99,
144
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing the attached screenshot of a webpage, please find the coordinates of the described element (with point). This element provides users with information about financing options or incentives related to the purchase of the iPhone 15 Pro. Interacting with this link likely leads to further details about financing options or special promotions for the product.",
"role": "user"
},
{
"content": "(55,132)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
pixmo-points-images/pixmo_364277_222309e7.jpg
|
<image>
Click on Fish
|
[
0.6067982316017151,
0.5042606592178345,
0.6466876268386841,
0.5477928519248962
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on Fish
|
[
781,
367,
832,
398
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on Fish",
"role": "user"
},
{
"content": "(806,382)",
"role": "assistant"
}
] | 1,288 | 1,288 | 728 |
|
autogui-images/autogui_2611289_fa643450.png
|
<image>
I'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element clears the search query, resets the search bar, and refocuses it for a new search input.
|
[
0.7612358927726746,
0.045767784118652344,
0.8550673723220825,
0.0945584625005722
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element clears the search query, resets the search bar, and refocuses it for a new search input.
|
[
170,
21,
191,
45
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element clears the search query, resets the search bar, and refocuses it for a new search input.",
"role": "user"
},
{
"content": "(180,33)",
"role": "assistant"
}
] | 224 | 224 | 476 |
|
pc-agent-e-images/data/events/screenshot/f31f_7e56b260_6.png
|
<image>
Click Properties in the context menu
|
[
0.04515242949128151,
0.6357046961784363,
0.19631481170654297,
0.6755132079124451
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click Properties in the context menu
|
[
36,
284,
159,
302
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick Properties in the context menu",
"role": "user"
},
{
"content": "(97,293)",
"role": "assistant"
}
] | 812 | 812 | 448 |
|
pixmo-points-images/pixmo_1178170_75eea1e0.png
|
<image>
Click on pencil icon
|
[
0.7458739876747131,
0.34783118963241577,
0.7778476476669312,
0.4103783965110779
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on pencil icon
|
[
772,
185,
805,
218
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on pencil icon",
"role": "user"
},
{
"content": "(788,201)",
"role": "assistant"
}
] | 1,036 | 1,036 | 532 |
|
pc-agent-e-images/data/events/screenshot/c99a_f5c2812e_1.png
|
<image>
Right-click on the WorkDocs folder
|
[
0.308989942073822,
0.105528824031353,
0.35654202103614807,
0.1438976377248764
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Right-click on the WorkDocs folder
|
[
198,
38,
229,
52
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nRight-click on the WorkDocs folder",
"role": "user"
},
{
"content": "(213,45)",
"role": "assistant"
}
] | 644 | 644 | 364 |
|
autogui-images/autogui_1540022_79eb5c22.png
|
<image>
Given this screenshot of a webpage, I'll describe an element; locate it for me (with point). This element serves as a navigation tool, allowing users on mobile devices to access the main menu of the website, providing quick access to various sections and links.
|
[
0.8594460487365723,
0.017318911850452423,
0.9432949423789978,
0.061482418328523636
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Given this screenshot of a webpage, I'll describe an element; locate it for me (with point). This element serves as a navigation tool, allowing users on mobile devices to access the main menu of the website, providing quick access to various sections and links.
|
[
192,
6,
211,
22
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nGiven this screenshot of a webpage, I'll describe an element; locate it for me (with point). This element serves as a navigation tool, allowing users on mobile devices to access the main menu of the website, providing quick access to various sections and links.",
"role": "user"
},
{
"content": "(201,14)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
pixmo-points-images/pixmo_1085716_b9553553.png
|
<image>
Click on X button
|
[
0.8428043723106384,
0.05076586827635765,
0.8752946853637695,
0.0953335389494896
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on X button
|
[
519,
24,
539,
45
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on X button",
"role": "user"
},
{
"content": "(529,34)",
"role": "assistant"
}
] | 616 | 616 | 476 |
|
pc-agent-e-images/data/events/screenshot/312a_b772380a_15.png
|
<image>
Select MacBook Air 13-inch (M3)
|
[
0.4128968119621277,
0.03657109662890434,
0.5546025037765503,
0.07105696946382523
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select MacBook Air 13-inch (M3)
|
[
682,
33,
916,
65
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect MacBook Air 13-inch (M3)",
"role": "user"
},
{
"content": "(799,49)",
"role": "assistant"
}
] | 1,652 | 1,652 | 924 |
|
pc-agent-e-images/data/events/screenshot/071a_21af5238_1.png
|
<image>
Open the settings menu
|
[
0.02314979024231434,
0.000560095882974565,
0.04394042491912842,
0.0326705276966095
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Open the settings menu
|
[
29,
0,
56,
23
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nOpen the settings menu",
"role": "user"
},
{
"content": "(42,11)",
"role": "assistant"
}
] | 1,288 | 1,288 | 728 |
|
autogui-images/autogui_081008_90b5bac5.png
|
<image>
Using the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element serves as a navigational tool, directing users to the Discover Home Page of the Snapchat platform, where they can explore various content, stories, and featured creators.
|
[
0.3693253993988037,
0.0158624816685915,
0.4184519350528717,
0.09630590677261353
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element serves as a navigational tool, directing users to the Discover Home Page of the Snapchat platform, where they can explore various content, stories, and featured creators.
|
[
310,
7,
351,
45
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element serves as a navigational tool, directing users to the Discover Home Page of the Snapchat platform, where they can explore various content, stories, and featured creators.",
"role": "user"
},
{
"content": "(330,26)",
"role": "assistant"
}
] | 840 | 840 | 476 |
|
pc-agent-e-images/data/events/screenshot/5166_c88f9a31_8.png
|
<image>
Click "All permissions" under Site permissions
|
[
0.7278218269348145,
0.6132866144180298,
0.7518049478530884,
0.6750849485397339
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click "All permissions" under Site permissions
|
[
468,
223,
484,
245
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick \"All permissions\" under Site permissions",
"role": "user"
},
{
"content": "(476,234)",
"role": "assistant"
}
] | 644 | 644 | 364 |
|
pc-agent-e-images/data/events/screenshot/1a3b_306dc151_5.png
|
<image>
Click the shortcut tab
|
[
0.11066772043704987,
0.3091736137866974,
0.15565025806427002,
0.33820992708206177
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click the shortcut tab
|
[
207,
328,
291,
359
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick the shortcut tab",
"role": "user"
},
{
"content": "(249,343)",
"role": "assistant"
}
] | 1,876 | 1,876 | 1,064 |
|
pc-agent-e-images/data/events/screenshot/f31f_bfd20564_14.png
|
<image>
Click the three-dot menu button
|
[
0.8079950213432312,
0.21865609288215637,
0.832258403301239,
0.25356414914131165
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click the three-dot menu button
|
[
1244,
189,
1281,
220
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick the three-dot menu button",
"role": "user"
},
{
"content": "(1262,204)",
"role": "assistant"
}
] | 1,540 | 1,540 | 868 |
|
pc-agent-e-images/data/events/screenshot/1a3b_f18c8114_7.png
|
<image>
Close the Windows C: Properties dialog
|
[
0.7654274702072144,
0.8898236751556396,
0.8212857842445374,
0.9268728494644165
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Close the Windows C: Properties dialog
|
[
878,
573,
942,
596
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClose the Windows C: Properties dialog",
"role": "user"
},
{
"content": "(910,584)",
"role": "assistant"
}
] | 1,148 | 1,148 | 644 |
|
autogui-images/autogui_1332134_fe9916ef.png
|
<image>
On this webpage screenshot, I will point out an element; please predict their exact coordinates (with point). This element triggers a navigation action that leads users to the sales team, providing them with an opportunity to inquire about the recruitment solutions or services offered by the webpage.
|
[
0.06949552148580551,
0.3546360433101654,
0.6697050333023071,
0.4219438433647156
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
On this webpage screenshot, I will point out an element; please predict their exact coordinates (with point). This element triggers a navigation action that leads users to the sales team, providing them with an opportunity to inquire about the recruitment solutions or services offered by the webpage.
|
[
15,
129,
150,
153
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nOn this webpage screenshot, I will point out an element; please predict their exact coordinates (with point). This element triggers a navigation action that leads users to the sales team, providing them with an opportunity to inquire about the recruitment solutions or services offered by the webpage.",
"role": "user"
},
{
"content": "(82,141)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_1971417_d395c4ff.png
|
<image>
In the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element provides access to a specific message or thread in the conversation.
|
[
0.12553757429122925,
0.16447006165981293,
0.398738831281662,
0.19382163882255554
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element provides access to a specific message or thread in the conversation.
|
[
115,
82,
368,
97
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element provides access to a specific message or thread in the conversation.",
"role": "user"
},
{
"content": "(241,89)",
"role": "assistant"
}
] | 924 | 924 | 504 |
|
autogui-images/autogui_730067_10d6813d.png
|
<image>
Please use the provided webpage screenshot to locate the element I describe (with point). This element allows users to access and manage their privacy preferences and cookie settings, enhancing their control over the webpage's data handling practices.
|
[
0.8683290481567383,
0.9188625812530518,
0.9454034566879272,
0.9714470505714417
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Please use the provided webpage screenshot to locate the element I describe (with point). This element allows users to access and manage their privacy preferences and cookie settings, enhancing their control over the webpage's data handling practices.
|
[
194,
334,
211,
353
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nPlease use the provided webpage screenshot to locate the element I describe (with point). This element allows users to access and manage their privacy preferences and cookie settings, enhancing their control over the webpage's data handling practices.",
"role": "user"
},
{
"content": "(202,343)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
pc-agent-e-images/data/events/screenshot/f31f_bfd20564_13.png
|
<image>
Click the uninstall confirmation button
|
[
0.7727115154266357,
0.2981424033641815,
0.8235890865325928,
0.3339079022407532
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click the uninstall confirmation button
|
[
605,
133,
645,
149
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick the uninstall confirmation button",
"role": "user"
},
{
"content": "(625,141)",
"role": "assistant"
}
] | 784 | 784 | 448 |
|
pixmo-points-images/pixmo_1263758_a337fa00.png
|
<image>
Click on phone number hyperlink
|
[
0.15718643367290497,
0.8574642539024353,
0.34501510858535767,
0.8950157165527344
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on phone number hyperlink
|
[
83,
504,
183,
526
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on phone number hyperlink",
"role": "user"
},
{
"content": "(133,515)",
"role": "assistant"
}
] | 532 | 532 | 588 |
|
autogui-images/autogui_642449_54e08f5d.png
|
<image>
From the image of this webpage, I will describe an element for you to locate (with point). This element provides access to information about the terms of using website documents.
|
[
0.40627825260162354,
0.7100644707679749,
0.46713030338287354,
0.7336174845695496
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
From the image of this webpage, I will describe an element for you to locate (with point). This element provides access to information about the terms of using website documents.
|
[
284,
278,
326,
287
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nFrom the image of this webpage, I will describe an element for you to locate (with point). This element provides access to information about the terms of using website documents.",
"role": "user"
},
{
"content": "(305,282)",
"role": "assistant"
}
] | 700 | 700 | 392 |
|
autogui-images/autogui_1711171_bc192aae.png
|
<image>
Based on this screenshot, I'll describe an element. Please pinpoint their exact locations (with point). This element provides users with the current price and percentage change of the '上證綜指' index, allowing them to quickly access detailed information about this index by clicking on it.
|
[
0.4972035884857178,
0.15762560069561005,
0.7282740473747253,
0.26009029150009155
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Based on this screenshot, I'll describe an element. Please pinpoint their exact locations (with point). This element provides users with the current price and percentage change of the '上證綜指' index, allowing them to quickly access detailed information about this index by clicking on it.
|
[
111,
57,
163,
94
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nBased on this screenshot, I'll describe an element. Please pinpoint their exact locations (with point). This element provides users with the current price and percentage change of the '上證綜指' index, allowing them to quickly access detailed information about this index by clicking on it.",
"role": "user"
},
{
"content": "(137,75)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_311284_6bebd626.png
|
<image>
Using the attached screenshot of a webpage, please find the coordinates of the described element (with point). This element represents a tab within a tablist on a Reddit user's profile page. Interacting with it allows users to view content related to the user's overview. The tablist, as a whole, enables users to navigate between different sections of the user's Reddit activity, such as their posts, comments, and overview.
|
[
0.015217560343444347,
0.38015612959861755,
0.26960882544517517,
0.45380234718322754
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using the attached screenshot of a webpage, please find the coordinates of the described element (with point). This element represents a tab within a tablist on a Reddit user's profile page. Interacting with it allows users to view content related to the user's overview. The tablist, as a whole, enables users to navigate between different sections of the user's Reddit activity, such as their posts, comments, and overview.
|
[
3,
138,
60,
165
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing the attached screenshot of a webpage, please find the coordinates of the described element (with point). This element represents a tab within a tablist on a Reddit user's profile page. Interacting with it allows users to view content related to the user's overview. The tablist, as a whole, enables users to navigate between different sections of the user's Reddit activity, such as their posts, comments, and overview.",
"role": "user"
},
{
"content": "(31,151)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
pixmo-points-images/pixmo_552878_2b7521b3.jpg
|
<image>
Click on tree branch
|
[
0,
0.1823996603488922,
0.9933056831359863,
0.44779983162879944
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on tree branch
|
[
0,
234,
723,
576
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on tree branch",
"role": "user"
},
{
"content": "(361,405)",
"role": "assistant"
}
] | 728 | 728 | 1,288 |
|
autogui-images/autogui_841645_568612ee.png
|
<image>
I'll describe certain an element on this webpage image; your task is to find their locations (with point). This element acts as a toggle for displaying or hiding a contextual menu on the webpage. Users can use it to access additional options or functionality related to the webpage content.
|
[
0.7558838129043579,
0.048698488622903824,
0.907478928565979,
0.06809814274311066
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll describe certain an element on this webpage image; your task is to find their locations (with point). This element acts as a toggle for displaying or hiding a contextual menu on the webpage. Users can use it to access additional options or functionality related to the webpage content.
|
[
169,
17,
203,
24
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll describe certain an element on this webpage image; your task is to find their locations (with point). This element acts as a toggle for displaying or hiding a contextual menu on the webpage. Users can use it to access additional options or functionality related to the webpage content.",
"role": "user"
},
{
"content": "(186,20)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
pixmo-points-images/pixmo_299876_c641a81c.png
|
<image>
Click on Button for placing pins.
|
[
0.40420541167259216,
0.010994798503816128,
0.4249095022678375,
0.05443045496940613
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on Button for placing pins.
|
[
1075,
15,
1130,
76
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on Button for placing pins.",
"role": "user"
},
{
"content": "(1102,45)",
"role": "assistant"
}
] | 2,660 | 2,660 | 1,400 |
|
autogui-images/autogui_210741_fc6026cd.png
|
<image>
Using the screenshot of this webpage, identify the coordinates of the element I describe (with point). This element activates the stopwatch timer, allowing users to track elapsed time.
|
[
0.664036214351654,
0.04622821509838104,
0.893070638179779,
0.1514739990234375
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using the screenshot of this webpage, identify the coordinates of the element I describe (with point). This element activates the stopwatch timer, allowing users to track elapsed time.
|
[
185,
23,
250,
76
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing the screenshot of this webpage, identify the coordinates of the element I describe (with point). This element activates the stopwatch timer, allowing users to track elapsed time.",
"role": "user"
},
{
"content": "(217,49)",
"role": "assistant"
}
] | 280 | 280 | 504 |
|
autogui-images/autogui_1491349_21080869.png
|
<image>
With this screenshot of a webpage, can you locate the element I describe (with point)? This element launches the Google Maps application and displays a sign-in prompt for quick access to the user's favorite places and better recommendations.
|
[
0.5376676917076111,
0.22617633640766144,
0.5968883633613586,
0.3677041530609131
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
With this screenshot of a webpage, can you locate the element I describe (with point)? This element launches the Google Maps application and displays a sign-in prompt for quick access to the user's favorite places and better recommendations.
|
[
225,
50,
250,
82
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nWith this screenshot of a webpage, can you locate the element I describe (with point)? This element launches the Google Maps application and displays a sign-in prompt for quick access to the user's favorite places and better recommendations.",
"role": "user"
},
{
"content": "(237,66)",
"role": "assistant"
}
] | 420 | 420 | 224 |
|
autogui-images/autogui_2270360_4948b31f.png
|
<image>
Please identify the coordinates of the webpage element I describe based on the provided screenshot (with point). This element acts as a trigger, directing users to a dedicated page or section dealing with membership or account management.
|
[
0.31874868273735046,
0.10366763919591904,
0.5639345049858093,
0.16053734719753265
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Please identify the coordinates of the webpage element I describe based on the provided screenshot (with point). This element acts as a trigger, directing users to a dedicated page or section dealing with membership or account management.
|
[
71,
37,
126,
58
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nPlease identify the coordinates of the webpage element I describe based on the provided screenshot (with point). This element acts as a trigger, directing users to a dedicated page or section dealing with membership or account management.",
"role": "user"
},
{
"content": "(98,47)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
pc-agent-e-images/data/events/screenshot/f31f_4e45dc19_1.png
|
<image>
Open Windows sound settings
|
[
0.34987562894821167,
0.9589566588401794,
0.37224701046943665,
0.9943132400512695
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Open Windows sound settings
|
[
587,
912,
625,
946
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nOpen Windows sound settings",
"role": "user"
},
{
"content": "(606,929)",
"role": "assistant"
}
] | 1,680 | 1,680 | 952 |
|
autogui-images/autogui_370456_7c50929f.png
|
<image>
I'll give textual clues about an element in this webpage screenshot; identify their coordinates (with point). This element provides access to a dedicated section of content, allowing users to explore related topics and information.
|
[
0.3783039152622223,
0.11196573078632355,
0.4229894280433655,
0.16099460422992706
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll give textual clues about an element in this webpage screenshot; identify their coordinates (with point). This element provides access to a dedicated section of content, allowing users to explore related topics and information.
|
[
360,
59,
402,
85
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll give textual clues about an element in this webpage screenshot; identify their coordinates (with point). This element provides access to a dedicated section of content, allowing users to explore related topics and information.",
"role": "user"
},
{
"content": "(381,72)",
"role": "assistant"
}
] | 952 | 952 | 532 |
|
autogui-images/autogui_1380164_349cade0.png
|
<image>
Using the screenshot of this webpage, identify the coordinates of the element I describe (with point). This element serves as a navigation link, providing users with access to information about ad choices, a common feature in digital advertising that allows users to customize the types of ads they see based on their preferences. Interacting with this link will likely redirect the user to a page where they can manage their ad settings.
|
[
0.41136759519577026,
0.6782881021499634,
0.5922714471817017,
0.7133407592773438
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using the screenshot of this webpage, identify the coordinates of the element I describe (with point). This element serves as a navigation link, providing users with access to information about ad choices, a common feature in digital advertising that allows users to customize the types of ads they see based on their preferences. Interacting with this link will likely redirect the user to a page where they can manage their ad settings.
|
[
92,
246,
132,
259
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing the screenshot of this webpage, identify the coordinates of the element I describe (with point). This element serves as a navigation link, providing users with access to information about ad choices, a common feature in digital advertising that allows users to customize the types of ads they see based on their preferences. Interacting with this link will likely redirect the user to a page where they can manage their ad settings.",
"role": "user"
},
{
"content": "(112,252)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
autogui-images/autogui_2522469_8a9bcde4.png
|
<image>
In the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element initiates a search query, allowing users to find specific news articles or topics within the website.
|
[
0.6559898257255554,
0.0695878192782402,
0.723107635974884,
0.13950380682945251
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element initiates a search query, allowing users to find specific news articles or topics within the website.
|
[
257,
15,
283,
31
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element initiates a search query, allowing users to find specific news articles or topics within the website.",
"role": "user"
},
{
"content": "(270,23)",
"role": "assistant"
}
] | 392 | 392 | 224 |
|
autogui-images/autogui_1540185_603086de.png
|
<image>
Please use the provided webpage screenshot to locate the element I describe (with point). This element provides access to general information about the platform.
|
[
0.04086923971772194,
0.6106998920440674,
0.09693783521652222,
0.6377390027046204
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Please use the provided webpage screenshot to locate the element I describe (with point). This element provides access to general information about the platform.
|
[
19,
170,
46,
178
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nPlease use the provided webpage screenshot to locate the element I describe (with point). This element provides access to general information about the platform.",
"role": "user"
},
{
"content": "(32,174)",
"role": "assistant"
}
] | 476 | 476 | 280 |
|
autogui-images/autogui_2340984_e3d5f69e.png
|
<image>
Based on the screenshot of the page, I give a text description and you give its corresponding location (with point). This element enables users to select all genres at once, facilitating a broader search or filtering of games.
|
[
0.010162952356040478,
0.4454185664653778,
0.24694238603115082,
0.4882473349571228
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Based on the screenshot of the page, I give a text description and you give its corresponding location (with point). This element enables users to select all genres at once, facilitating a broader search or filtering of games.
|
[
2,
162,
55,
177
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nBased on the screenshot of the page, I give a text description and you give its corresponding location (with point). This element enables users to select all genres at once, facilitating a broader search or filtering of games.",
"role": "user"
},
{
"content": "(28,169)",
"role": "assistant"
}
] | 224 | 224 | 364 |
|
pixmo-points-images/pixmo_1812547_d5e06d5a.jpg
|
<image>
Click on tree
|
[
0.004772472195327282,
0.37101224064826965,
0.9800264239311218,
0.7146111130714417
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on tree
|
[
5,
654,
1152,
1260
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on tree",
"role": "user"
},
{
"content": "(578,957)",
"role": "assistant"
}
] | 1,176 | 1,176 | 1,764 |
|
seeclick-images/fdb0d6a7eb1eec8c959b0e99369fc127.png
|
<image>
Click on "9"
|
[
0.7140202522277832,
0.7215663194656372,
0.7257070541381836,
0.746530294418335
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on "9"
|
[
1819,
1030,
1849,
1066
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on \"9\"",
"role": "user"
},
{
"content": "(1834,1048)",
"role": "assistant"
}
] | 2,548 | 2,548 | 1,428 |
|
autogui-images/autogui_1191219_e327fb82.png
|
<image>
In the provided web page image, I'll describe a specific element. Identify their locations, please (with point). This element provides access to business-related content or news.
|
[
0.3206084072589874,
0.17807430028915405,
0.4063777029514313,
0.252578467130661
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In the provided web page image, I'll describe a specific element. Identify their locations, please (with point). This element provides access to business-related content or news.
|
[
143,
44,
182,
63
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn the provided web page image, I'll describe a specific element. Identify their locations, please (with point). This element provides access to business-related content or news.",
"role": "user"
},
{
"content": "(162,53)",
"role": "assistant"
}
] | 448 | 448 | 252 |
|
pc-agent-e-images/data/events/screenshot/cc4d_6fca3356_1.png
|
<image>
Click "Manage favorites now
|
[
0.30848991870880127,
0.08932802081108093,
0.38625526428222656,
0.1099618524312973
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click "Manage favorites now
|
[
285,
47,
356,
58
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick \"Manage favorites now",
"role": "user"
},
{
"content": "(320,52)",
"role": "assistant"
}
] | 924 | 924 | 532 |
|
pixmo-points-images/pixmo_942264_00566fa1.jpeg
|
<image>
Click on actions dropdown
|
[
0.7684376239776611,
0.813692569732666,
0.8193295001983643,
0.8409024477005005
] |
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on actions dropdown
|
[
559,
341,
596,
353
] |
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on actions dropdown",
"role": "user"
},
{
"content": "(577,347)",
"role": "assistant"
}
] | 728 | 728 | 420 |
End of preview. Expand
in Data Studio
YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/datasets-cards)
easyr1-grounding-dataset-10k-omniparser-filtered-4MP
This dataset was generated using the EasyR1 grounding dataset pipeline.
Generation Details
- Generated on: 2025-08-25 17:27:37 UTC
- Script:
push_easyr1_to_hf.py - Data directory:
/lustre/fsw/portfolios/nvr/users/aawadalla/LLaMA-Factory/data
Parameters Used
- Maximum samples: 10000
- Image resize (max megapixels): 4.0 MP
- Minimum native image resolution: 0.0 MP
- Prompt format:
gta1 - Output format:
coordinates - Random seed: 42
- Resampling enabled: False
- Icon upsampling ratio: Disabled (random sampling)
- pc-agent-e deduplication: False
Dataset Groups
The following JSON/JSONL files were used to create this dataset:
Dataset Group 1
Files (intersection of kept samples across all files):
- grounding-data-filters/pixmo-points-qwen_tool_call-not_grounded-Qwen_Qwen2.5-VL-7B-Instruct-qwen_tool_call.jsonl
- grounding-data-filters/pixmo-points-gta1-correctly_grounded-HelloKKMe_GTA1-7B-gta1.jsonl
Dataset Group 2
Files (intersection of kept samples across all files):
- grounding-data-filters/autogui-grounding-only-qwen_tool_call-not_grounded-Qwen_Qwen2.5-VL-7B-Instruct-qwen_tool_call.jsonl
- grounding-data-filters/autogui-grounding-only-gta1-correctly_grounded-HelloKKMe_GTA1-7B-gta1.jsonl
Dataset Group 3
Files (intersection of kept samples across all files):
- grounding-data-filters/seeclick-qwen_tool_call-not_grounded-Qwen_Qwen2.5-VL-7B-Instruct-qwen_tool_call.jsonl
- grounding-data-filters/seeclick-gta1-correctly_grounded-HelloKKMe_GTA1-7B-gta1.jsonl
Dataset Group 4
- grounding-data-filters/pc-e-grounding-only-claude-instructions-qwen_tool_call-not_grounded-Qwen_Qwen2.5-VL-7B-Instruct-qwen_tool_call.jsonl
Dataset Statistics
- Total training samples: 10000
- Image dimensions: Variable
- Columns: image_path, prompt, normalized_bbox, images, easyr1_prompt, bbox, messages, original_image_width, image_width, image_height
System Prompt
The following system prompt is used for this dataset:
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
Sample Entry
- User prompt:
I'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element acts as a navigation link, directing users to the WhatsApp extension page. It provides users with essential information about the extension, such as its name and popularity, through the displayed rating and number of ratings. Interacting with this link enables users to explore the WhatsApp extension in more detail.
- Assistant response: (139,210)
- Bounding box: [113, 196, 166, 224]
- Image path: autogui-images/autogui_2500717_92944f8f.png
Usage
from datasets import load_dataset
dataset = load_dataset("mlfoundations-cua-dev/easyr1-grounding-dataset-10k-omniparser-filtered-4MP")
# Access the training data
train_data = dataset['train']
# Example: Get the first sample
sample = train_data[0]
images = sample['images']
messages = sample['messages']
bbox = sample['bbox']
Prompt Formats
gta1
Standard GTA1 format without resolution information. Outputs coordinates in (x,y) format.
License
Please refer to the original dataset licenses for usage restrictions.
- Downloads last month
- 144