Spaces:

blowing-up-groundhogs
/

README

Running

App Files Files Community

vpippi commited on Feb 7

Commit

3a67230

verified ·

1 Parent(s): 79fe3df

Update README.md

Browse files

Files changed (1) hide show

README.md +93 -87

README.md CHANGED Viewed

@@ -7,135 +7,141 @@ sdk: static
 pinned: false
 ---
-# Welcome to the AI & Computer Vision Organization
-**Headed by [Silvia Cascianelli](https://personale.unimore.it/rubrica/dettaglio/scascianelli)**
-This repository hosts the source code for our organization's main website and showcases our research projects, recent updates, and the people that make up our vibrant AI community. Whether you’re interested in our ongoing projects, would like to see where we publish, or simply want to say hello, our site is the best place to start.
 ---
 ## Table of Contents
-1. [About](#about)
-2. [Features](#features)
-3. [Project Structure](#project-structure)
-4. [How to Use](#how-to-use)
-5. [Sections Overview](#sections-overview)
-6. [Contributing](#contributing)
-7. [License](#license)
-8. [Contact](#contact)
 ---
-## About
-We are a team of **AI and Computer Vision** researchers, engineers, and students, led by **Dr. Silvia Cascianelli**. Our mission is to push forward the boundaries of AI technology—especially in areas such as **image generation**, **handwriting imitation**, and **document understanding**—while fostering a community of mentorship and collaboration.
-Silvia is a passionate AI researcher and mentor to aspiring AI scientists. Her portfolio highlights some of the cutting-edge work being done within this organization, as well as showcasing the successes of our graduate students and interns.
----
-## Features
-- **Responsive Web Design**: Optimized for mobile, tablet, and desktop devices.
-- **Projects Highlight**: Showcases recent and noteworthy AI and Computer Vision projects (e.g., Diffusion Models, Handwriting Imitation, Document Understanding).
-- **Mentorees Section**: A heartfelt spotlight on the students, interns, and collaborators supervised or co-supervised by Silvia.
-- **Latest Updates**: A regularly updated section sharing news about lectures, workshops, seminars, and other exciting community events.
-- **External Links**: Quick references to Google Scholar, LinkedIn, GitHub, and more, to stay connected with the team’s academic and professional footprint.
----
-## Project Structure
-```
-.
-├── assets
-│   ├── fonts
-│   ├── images
-│   │   ├── work
-│   │   ├── testimonials
-│   │   ├── skills
-│   │   └── social-links
-│   └── ...
-├── style.css        // Main stylesheet
-├── script.js        // Site-wide JavaScript
-└── index.html       // Main web page
-```
-- **index.html**: The landing page that structures all sections (header, projects, mentorees, external links, latest updates, and contact).
-- **style.css**: Styles for layout, typography, and responsiveness.
-- **script.js**: Small JavaScript utilities (like theme switching) and event handling.
-- **assets/**: Contains fonts, images, icons, and other required files for the site.
----
-## How to Use
-1. **Clone or Download**
-   ```bash
-   git clone https://github.com/YourOrganization/YourRepoName.git
-   ```
-2. **Open Locally**
-   - Open `index.html` in your preferred web browser.
-   - Make sure the `assets/` folder is in the same directory as `index.html` so that images and styles load correctly.
-3. **Explore**
-   - Navigate through the **Recent Projects**, **Mentorees**, and **Latest Updates** sections to learn about our work.
-   - Use the **External Links** section to access relevant social and academic profiles.
----
-## Sections Overview
-1. **Header**
-   Introduces **Silvia Cascianelli**, an AI researcher and aspiring mentor, featuring quick links for visitors to reach out or explore the site.
-2. **Recent Projects**
-   - **Image Generation**: Research on lightweight and efficient image generation leveraging Diffusion Models.
-   - **Handwriting Imitation**: Methods for synthesizing stylized text images, complete with evaluation metrics and relevant applications.
-   - **Document Understanding**: Techniques for extracting meaningful information from 2D and 3D document images, including historical papyri and modern documents.
-3. **Mentorees**
-   Highlights current and past students, interns, and collaborators, celebrating their unique contributions and growth.
-4. **External Links**
-   Quick access to [CV](https://drive.google.com/file/d/1bx4iY61ZWnv2AFsm2TZh-xDytabNN9uv), [Google Scholar](https://scholar.google.com/citations?hl=it&user=utmt89wAAAAJ), [LinkedIn](https://www.linkedin.com/in/silvia-cascianelli-330760104/), [UniMoRe](https://personale.unimore.it/rubrica/dettaglio/scascianelli), and [GitHub](https://github.com/silviaCascianelli).
-5. **Latest Updates**
-   News about **workshops**, **course lectures**, **internships**, **research visits**, and **conference service roles** (e.g., serving as an Area Chair at major AI/CV conferences).
-6. **Contact**
-   Encourages direct communication via LinkedIn or email. Features a friendly illustration of Silvia and a personal note to welcome questions and collaboration ideas.
----
-## Contributing
-We are open to collaborations that align with our mission in **AI and Computer Vision**. If you’d like to:
-- Report a bug
-- Request a feature
-- Collaborate on a project
-- Suggest new design ideas for the website
-Please [open an issue](../../issues) or [submit a pull request](../../pulls). We welcome feedback from the community!
 ---
-## License
-Unless otherwise noted, the contents of this repository are distributed under the **MIT License**. See [LICENSE](LICENSE) for more details.
 ---
 ## Contact
-For any inquiries, speaking engagements, or collaborations, feel free to reach out:
 - **Email**: scascianelli\[at\]unimore\[dot\]it
 - **LinkedIn**: [linkedin.com/in/silvia-cascianelli-330760104](https://www.linkedin.com/in/silvia-cascianelli-330760104/)
-- **UniMoRe**: [personale.unimore.it/rubrica/dettaglio/scascianelli](https://personale.unimore.it/rubrica/dettaglio/scascianelli)
-Thank you for visiting our organization’s repository!

 pinned: false
 ---
+# AI & Computer Vision Research Hub
+**Led by Dr. Silvia Cascianelli**
+Welcome to our AI & Computer Vision research hub. We focus on exploring cutting-edge techniques in **image generation**, **handwriting imitation**, and **document understanding**, while fostering an environment that emphasizes mentorship and collaboration. Below, you’ll find highlights of our recent projects, the brilliant minds collaborating with us, and the latest updates from our community.
 ---
 ## Table of Contents
+1. [Introduction](#introduction)
+2. [Recent Projects](#recent-projects)
+   - [Image Generation](#image-generation)
+   - [Handwriting Imitation](#handwriting-imitation)
+   - [Document Understanding](#document-understanding)
+3. [Our Team & Mentorees](#our-team--mentorees)
+4. [Latest Updates](#latest-updates)
+5. [External Links](#external-links)
+6. [Contact](#contact)
 ---
+## Introduction
+We are a group of enthusiastic researchers, students, and practitioners delving into challenges at the forefront of AI. Under the guidance of **Dr. Silvia Cascianelli**, we tackle complex tasks in AI-driven content creation, strive to replicate distinctive handwriting styles, and unlock insights from historical and modern documents. Our mission is not only to advance these research areas but also to foster a nurturing environment for emerging researchers.
+---
+## Recent Projects
+### Image Generation
+We specialize in developing efficient and lightweight methods to generate images with desired characteristics. Our work particularly explores how **Diffusion Models** can be adapted at inference time to produce semantically coherent or uniquely formatted images.
+- **Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas**
+  [Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli, Rita Cucchiara]
+  [arXiv:2408.15660](https://arxiv.org/abs/2408.15660)
+- **Alfie: Democratising RGBA Image Generation With No $$$**
+  [Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli, Rita Cucchiara]
+  [arXiv:2408.14826](https://arxiv.org/abs/2408.14826)
+### Handwriting Imitation
+Our research explores algorithms to generate images of text in various handwriting styles, how to evaluate the generated results, and how these findings can be applied in real-world contexts (e.g., personalized text rendering).
+- **VATr++: Choose Your Words Wisely for Handwritten Text Generation**
+  [Bram Vanherle, Vittorio Pippi, Silvia Cascianelli, Nick Michiels, Frank Von Reeth, Rita Cucchiara]
+  [arXiv:2402.10798](https://arxiv.org/abs/2402.10798)
+- **Handwritten Text Generation from Visual Archetypes**
+  [Vittorio Pippi, Silvia Cascianelli, Rita Cucchiara]
+  [arXiv:2303.15269](https://arxiv.org/abs/2303.15269)
+- **HWD: A Novel Evaluation Score for Styled Handwritten Text Generation**
+  [Vittorio Pippi, Fabio Quattrini, Silvia Cascianelli, Rita Cucchiara]
+  [arXiv:2310.20316](https://arxiv.org/abs/2310.20316)
+- **How to Choose Pretrained HTR Models for Single Writer Fine-Tuning**
+  [Vittorio Pippi, Silvia Cascianelli, Christopher Kermorvant, Rita Cucchiara]
+  [arXiv:2305.02593](https://arxiv.org/abs/2305.02593)
+### Document Understanding
+From analyzing complex 2D/3D scans of historical papyri to modern ESG reports, our team builds systems to detect ink traces, parse text, interpret layout, and uncover valuable writer-centric details.
+- **μgat: Improving Single-Page Document Parsing by Providing Multi-Page Context**
+  [Carmine Zaccagnino, Fabio Quattrini, Silvia Cascianelli, Laura Righi, Rita Cucchiara]
+  [arXiv:2408.15646](https://arxiv.org/abs/2408.15646)
+- **Volumetric FFC for Detecting Ink on the Carbonized Herculaneum Papyri**
+  [Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli, Rita Cucchiara]
+  [arXiv:2308.05070](https://arxiv.org/abs/2308.05070)
+- **Evaluating Synthetic Pre-Training for Handwriting Processing Tasks**
+  [Vittorio Pippi, Silvia Cascianelli, Lorenzo Baraldi, Rita Cucchiara]
+  [arXiv:2304.01842](https://arxiv.org/abs/2304.01842)
+- **The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition**
+  [Silvia Cascianelli, Vittorio Pippi, Martin Maarand, Marcella Cornia, Lorenzo Baraldi, Christopher Kermorvant, Rita Cucchiara]
+  [arXiv:2208.08109](https://arxiv.org/abs/2208.08109)
+- **Boosting Modern and Historical HTR with Deformable Convolutions**
+  [Silvia Cascianelli, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara]
+  [arXiv:2305.02593](https://arxiv.org/abs/2305.02593)
+---
+## Our Team & Mentorees
+A significant part of our success comes from a dedicated group of researchers, interns, and students who collaborate with Dr. Cascianelli:
+- **Vittorio Pippi**: PhD student (National PhD in AI); recently interned at Amazon Research Berlin.
+  *Grounded, generous, and sharp.*
+- **Fabio Quattrini**: PhD student at UniMoRe; also interning at Amazon Research Berlin.
+  *Creative, kind, and direct.*
+- **Carmine Zaccagnino**: Recent MSc graduate and current research intern at UniMoRe.
+  *Hardworking, proactive, and passionate.*
+- **Pau Torras Coloma**: PhD student at CVC-UAB; spent 1.5 months at UniMoRe as a visiting intern.
+  *Committed, curious, and adaptable.*
+- **Bram Vanherle**: CV Engineer at Colruyt Group Smart Innovation; spent 5 months of internship at UniMoRe.
+  *Concrete, easygoing, and consistently solid.*
+---
+## Latest Updates
+Stay tuned for news on our lectures, workshops, and conference appearances:
+- **AI Governance Lab**: Served as one of the lecturers for the [AI Governance Lab course](https://panetta.it/ai-governance-lab/).
+- **InsAIde Article**: Co-authored a tech post with Davide Morelli in the [InsAIde newsletter](https://insaide.substack.com/p/insaide-51-llms-can-implement-rag).
+- **ECCV2024**: Fresh experiences and seeds planted at ECCV2024 in Milan—exciting projects ahead!
+- **AC @CVPR2025**: Proud to serve as an Area Chair for CVPR2025.
+- **AI4DH Workshop @ECCV2025**: Co-organizing the third edition of the “AI for Digital Humanities” workshop at ECCV2025.
+- **Flash Seminar @Huawei**: Engaging seminar at the Amsterdam Huawei Research Center on our research directions.
+- **Bram’s Defense**: Dr. Cascianelli was part of the PhD jury for Bram Vanherle’s successful defense at UHasselt.
+- **ICDAR2024**: A rewarding conference in Athens, feeling at home in the ICDAR community.
+- **ADAPDA Workshop @ICDAR2024**: The second edition of the “Automatically Domain-Adapted and Personalized Document Analysis” workshop saw great participation.
+- **AC @ECCV2024**: Dr. Cascianelli will also be serving as an Area Chair at ECCV2024.
 ---
+## External Links
+Explore more about Dr. Cascianelli’s publications, professional profiles, and contact details:
+- **[CV](https://drive.google.com/file/d/1bx4iY61ZWnv2AFsm2TZh-xDytabNN9uv/view)**
+- **[Google Scholar](https://scholar.google.com/citations?hl=it&user=utmt89wAAAAJ)**
+- **[LinkedIn](https://www.linkedin.com/in/silvia-cascianelli-330760104/)**
+- **[UniMoRe Profile](https://personale.unimore.it/rubrica/dettaglio/scascianelli)**
+- **[GitHub](https://github.com/silviaCascianelli)**
 ---
 ## Contact
+Thank you for your interest! If you find our work compelling or would like to discuss potential collaborations, please reach out:
 - **Email**: scascianelli\[at\]unimore\[dot\]it
 - **LinkedIn**: [linkedin.com/in/silvia-cascianelli-330760104](https://www.linkedin.com/in/silvia-cascianelli-330760104/)
+We look forward to hearing from you!
+_**© 2025 AI & Computer Vision Research Hub, led by Dr. Silvia Cascianelli**_