Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -7,112 +7,55 @@ sdk: static
|
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
-
# AI & Computer Vision Research Hub
|
11 |
-
|
12 |
|
13 |
-
Welcome to our
|
14 |
|
15 |
---
|
16 |
|
17 |
-
##
|
18 |
-
1. [Introduction](#introduction)
|
19 |
-
2. [Recent Projects](#recent-projects)
|
20 |
-
- [Image Generation](#image-generation)
|
21 |
-
- [Handwriting Imitation](#handwriting-imitation)
|
22 |
-
- [Document Understanding](#document-understanding)
|
23 |
-
3. [Our Team](#our-team--mentorees)
|
24 |
-
|
25 |
-
---
|
26 |
-
|
27 |
-
## Introduction
|
28 |
-
We are a group of researchers delving into challenges at the forefront of AI. We tackle complex tasks in AI-driven content creation, strive to replicate distinctive handwriting styles, and unlock insights from historical and modern documents.
|
29 |
-
|
30 |
-
---
|
31 |
-
|
32 |
-
## Recent Projects
|
33 |
|
34 |
### Image Generation
|
35 |
-
|
36 |
-
|
37 |
-
- **Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas**
|
38 |
-
[Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli, Rita Cucchiara]
|
39 |
[arXiv:2408.15660](https://arxiv.org/abs/2408.15660)
|
40 |
-
|
41 |
-
- **Alfie: Democratising RGBA Image Generation With No $$$**
|
42 |
-
[Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli, Rita Cucchiara]
|
43 |
[arXiv:2408.14826](https://arxiv.org/abs/2408.14826)
|
44 |
|
45 |
### Handwriting Imitation
|
46 |
-
|
47 |
-
|
48 |
-
- **VATr++: Choose Your Words Wisely for Handwritten Text Generation**
|
49 |
-
[Bram Vanherle, Vittorio Pippi, Silvia Cascianelli, Nick Michiels, Frank Von Reeth, Rita Cucchiara]
|
50 |
[arXiv:2402.10798](https://arxiv.org/abs/2402.10798)
|
51 |
-
|
52 |
- **Handwritten Text Generation from Visual Archetypes**
|
53 |
-
[Vittorio Pippi, Silvia Cascianelli, Rita Cucchiara]
|
54 |
[arXiv:2303.15269](https://arxiv.org/abs/2303.15269)
|
55 |
-
|
56 |
-
- **HWD: A Novel Evaluation Score for Styled Handwritten Text Generation**
|
57 |
-
[Vittorio Pippi, Fabio Quattrini, Silvia Cascianelli, Rita Cucchiara]
|
58 |
[arXiv:2310.20316](https://arxiv.org/abs/2310.20316)
|
59 |
-
|
60 |
-
- **How to Choose Pretrained HTR Models for Single Writer Fine-Tuning**
|
61 |
-
[Vittorio Pippi, Silvia Cascianelli, Christopher Kermorvant, Rita Cucchiara]
|
62 |
[arXiv:2305.02593](https://arxiv.org/abs/2305.02593)
|
63 |
|
64 |
### Document Understanding
|
65 |
-
|
66 |
-
|
67 |
-
- **μgat: Improving Single-Page Document Parsing by Providing Multi-Page Context**
|
68 |
-
[Carmine Zaccagnino, Fabio Quattrini, Silvia Cascianelli, Laura Righi, Rita Cucchiara]
|
69 |
[arXiv:2408.15646](https://arxiv.org/abs/2408.15646)
|
70 |
-
|
71 |
-
- **Volumetric FFC for Detecting Ink on the Carbonized Herculaneum Papyri**
|
72 |
-
[Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli, Rita Cucchiara]
|
73 |
[arXiv:2308.05070](https://arxiv.org/abs/2308.05070)
|
74 |
-
|
75 |
-
- **Evaluating Synthetic Pre-Training for Handwriting Processing Tasks**
|
76 |
-
[Vittorio Pippi, Silvia Cascianelli, Lorenzo Baraldi, Rita Cucchiara]
|
77 |
[arXiv:2304.01842](https://arxiv.org/abs/2304.01842)
|
78 |
-
|
79 |
-
- **The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition**
|
80 |
-
[Silvia Cascianelli, Vittorio Pippi, Martin Maarand, Marcella Cornia, Lorenzo Baraldi, Christopher Kermorvant, Rita Cucchiara]
|
81 |
[arXiv:2208.08109](https://arxiv.org/abs/2208.08109)
|
82 |
-
|
83 |
-
- **Boosting Modern and Historical HTR with Deformable Convolutions**
|
84 |
-
[Silvia Cascianelli, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara]
|
85 |
[arXiv:2305.02593](https://arxiv.org/abs/2305.02593)
|
86 |
|
87 |
---
|
88 |
|
89 |
## Our Team
|
90 |
-
|
91 |
-
|
92 |
-
- **[
|
93 |
-
|
94 |
-
|
95 |
-
- **[
|
96 |
-
*Grounded, generous, and sharp.*
|
97 |
-
|
98 |
-
- **[Fabio Quattrini](https://www.linkedin.com/in/fabio-quattrini-8b0a18244/)**: PhD student at UniMoRe; also interning at Amazon Research Berlin.
|
99 |
-
*Creative, kind, and direct.*
|
100 |
-
|
101 |
-
- **[Carmine Zaccagnino](https://github.com/carzacc)**: Recent MSc graduate and current research intern at UniMoRe.
|
102 |
-
*Hardworking, proactive, and passionate.*
|
103 |
-
|
104 |
-
- **[Pau Torras Coloma](https://www.linkedin.com/in/pau-torras-coloma-69918a1b0/?originalSubdomain=es)**: PhD student at CVC-UAB; spent 1.5 months at UniMoRe as a visiting intern.
|
105 |
-
*Committed, curious, and adaptable.*
|
106 |
-
|
107 |
-
- **[Bram Vanherle](https://bvanherle.github.io/)**: CV Engineer at Colruyt Group Smart Innovation; spent 5 months of internship at UniMoRe.
|
108 |
-
*Concrete, easygoing, and consistently solid.*
|
109 |
|
110 |
---
|
111 |
|
112 |
## Contact
|
113 |
-
|
114 |
-
|
115 |
-
- **Email**: scascianelli\[at\]unimore\[dot\]it
|
116 |
-
- **LinkedIn**: [linkedin.com/in/silvia-cascianelli-330760104](https://www.linkedin.com/in/silvia-cascianelli-330760104/)
|
117 |
-
|
118 |
-
We look forward to hearing from you!
|
|
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
+
# AI & Computer Vision Research Hub
|
11 |
+
*Led by Dr. Silvia Cascianelli*
|
12 |
|
13 |
+
Welcome to our research hub, where we explore advanced techniques in **image generation**, **handwriting imitation**, and **document understanding** in a collaborative, mentoring environment.
|
14 |
|
15 |
---
|
16 |
|
17 |
+
## Projects
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
### Image Generation
|
20 |
+
- **Merging and Splitting Diffusion Paths for Panoramas**
|
|
|
|
|
|
|
21 |
[arXiv:2408.15660](https://arxiv.org/abs/2408.15660)
|
22 |
+
- **Alfie: Democratising RGBA Image Generation**
|
|
|
|
|
23 |
[arXiv:2408.14826](https://arxiv.org/abs/2408.14826)
|
24 |
|
25 |
### Handwriting Imitation
|
26 |
+
- **VATr++: Handwritten Text Generation**
|
|
|
|
|
|
|
27 |
[arXiv:2402.10798](https://arxiv.org/abs/2402.10798)
|
|
|
28 |
- **Handwritten Text Generation from Visual Archetypes**
|
|
|
29 |
[arXiv:2303.15269](https://arxiv.org/abs/2303.15269)
|
30 |
+
- **HWD: Evaluation for Handwritten Text Generation**
|
|
|
|
|
31 |
[arXiv:2310.20316](https://arxiv.org/abs/2310.20316)
|
32 |
+
- **Pretrained HTR Models for Fine-Tuning**
|
|
|
|
|
33 |
[arXiv:2305.02593](https://arxiv.org/abs/2305.02593)
|
34 |
|
35 |
### Document Understanding
|
36 |
+
- **μgat: Document Parsing with Multi-Page Context**
|
|
|
|
|
|
|
37 |
[arXiv:2408.15646](https://arxiv.org/abs/2408.15646)
|
38 |
+
- **Volumetric FFC for Ink Detection on Papyri**
|
|
|
|
|
39 |
[arXiv:2308.05070](https://arxiv.org/abs/2308.05070)
|
40 |
+
- **Synthetic Pre-Training for Handwriting Processing**
|
|
|
|
|
41 |
[arXiv:2304.01842](https://arxiv.org/abs/2304.01842)
|
42 |
+
- **The LAM Dataset for Handwritten Text Recognition**
|
|
|
|
|
43 |
[arXiv:2208.08109](https://arxiv.org/abs/2208.08109)
|
44 |
+
- **Boosting HTR with Deformable Convolutions**
|
|
|
|
|
45 |
[arXiv:2305.02593](https://arxiv.org/abs/2305.02593)
|
46 |
|
47 |
---
|
48 |
|
49 |
## Our Team
|
50 |
+
- **[Silvia Cascianelli](https://www.silviacascianelli.com)** – Assistant Professor
|
51 |
+
- **[Vittorio Pippi](https://www.linkedin.com/in/vittorio-pippi/)** – PhD Student
|
52 |
+
- **[Fabio Quattrini](https://www.linkedin.com/in/fabio-quattrini-8b0a18244/)** – PhD Student
|
53 |
+
- **[Carmine Zaccagnino](https://github.com/carzacc)** – Research Intern
|
54 |
+
- **[Pau Torras Coloma](https://www.linkedin.com/in/pau-torras-coloma-69918a1b0/)** – PhD Student
|
55 |
+
- **[Bram Vanherle](https://bvanherle.github.io/)** – CV Engineer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
---
|
58 |
|
59 |
## Contact
|
60 |
+
**Email:** scascianelli[at]unimore[dot]it
|
61 |
+
**LinkedIn:** [Silvia Cascianelli](https://www.linkedin.com/in/silvia-cascianelli-330760104/)
|
|
|
|
|
|
|
|