docs(readme): fix typo in README.md
#5
by
BjornMelin
- opened
README.md
CHANGED
|
@@ -27,7 +27,7 @@ In the past five months since Qwen2-VL’s release, numerous developers have bui
|
|
| 27 |
|
| 28 |
* **Being agentic**: Qwen2.5-VL directly plays as a visual agent that can reason and dynamically direct tools, which is capable of computer use and phone use.
|
| 29 |
|
| 30 |
-
* **Understanding long videos and capturing events**: Qwen2.5-VL can comprehend videos of over 1 hour, and this time it has a new ability of
|
| 31 |
|
| 32 |
* **Capable of visual localization in different formats**: Qwen2.5-VL can accurately localize objects in an image by generating bounding boxes or points, and it can provide stable JSON outputs for coordinates and attributes.
|
| 33 |
|
|
|
|
| 27 |
|
| 28 |
* **Being agentic**: Qwen2.5-VL directly plays as a visual agent that can reason and dynamically direct tools, which is capable of computer use and phone use.
|
| 29 |
|
| 30 |
+
* **Understanding long videos and capturing events**: Qwen2.5-VL can comprehend videos of over 1 hour, and this time it has a new ability of capturing event by pinpointing the relevant video segments.
|
| 31 |
|
| 32 |
* **Capable of visual localization in different formats**: Qwen2.5-VL can accurately localize objects in an image by generating bounding boxes or points, and it can provide stable JSON outputs for coordinates and attributes.
|
| 33 |
|