ItalNet:
Connecting the early career Italian computer vision and pattern recognition community
Embedded Files
When: 16 September 2025
Where: ICIAP 2025, Sapienza University of Rome (Rome, Italy)
Computer vision and pattern recognition are experiencing unprecedented growth, with thousands of research papers presented at top venues. Within these advances, Italy is playing its role. Over the years, the contribution of Italian research groups to top conferences has kept growing, with more and more articles coming from our community as well as the number of attendees (e.g., from 64 of CVPR 2019, to 118 of CVPR 2024). While ideas keep growing, there is a lack of a space where our community can share ideas, research achievements, or, simply, just facilitate its members to know each other. This is more important for young researchers who did not have the time to build as many connections as the more senior members.
This workshop aims to create such space by (1) inviting early career computer vision researchers based in Italy to present their recent works accepted or presented in the top recent venues; and (2) invite successful researchers to share experiences and career advice to help younger members navigate this continuously evolving landscape. The goal is to create an event where the younger members of our community can share research, get inspired, and, most importantly, connect.
Contribute:
Contribute:
Are you a young researcher working in an Italian institution?
Do you have a paper on computer vision and pattern recently accepted/presented in a top venue, e.g., ECCV 2024, NeurIPS 2024, ICLR 2025, CVPR 2025, ICML 2025, ICCV 2025?
If you would like to present your work, please reach us out! Selected works will be presented during the workshop as orals. You can submit your proposal also through this form.
Note: The call for contributions is closed! We are waiting you in Rome for the 1st edition!
Program
Program
The workshop will consist of keynote talks (35min + 5min questions) and paper presentations (7min) from young researchers, presenting their works. The latter will be grouped in sessions of 3/4 papers each, with a shared Q&A of 5 minutes at the end.
09.00 - 09.20 Opening remarks
09.20 - 10.00 Keynote 1: Vicky Kalogeiton
10.00 - 10.40 Session 1: Learning representations, networks, and tasks
Niccolò Biondi - "Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements", CVPR 2024 (link).
Lorenzo Braccaioli - "Unsupervised Meta-Learning via In-Context Learning", ICLR 2025 (link).
Mujtaba Hussain Mirza and Maria Rosaria Briglia - "Shedding More Light on Robust Classifiers under the lens of Energy-based Models", ECCV 2024 (link).
10.40 - 11.00 Coffee break ☕
11.00 - 11.40 Session 2: 3D vision
11.00 - 11.40 Session 2: 3D vision
Claudio Ferrari - "Scantalk: 3d talking heads from unregistered scans", ECCV 2024 (link).
Francesco Di Sario - "Boost Your NeRF: A Model-Agnostic Mixture of Experts Framework for High Quality and Efficient Rendering", ECCV 2024 (link).
Adeela Islam - "Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving", NeuRIPS 2024 (link).
11.40 - 12.20 Session 3: Information retrieval in the open world
Sara Sarto - "Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval", CVPR 2025 (link).
Tommaso Campari - "Training-free Embodied AI Agents for Open-world Tasks", CVPR 2025 (link).
Luca Collorone - "MonSTeR: a Unified Model for Motion, Scene, Text Retrieval", ICCV 2025.
12.20 - 13.00 Keynote 2: Fabio Cermelli
13.00 - 14.30 Lunch break 🍝
14.30 - 15.10 Keynote 3: Giovanni Maria Farinella
15.10 - 15.50 Session 4: Video understanding
Luigi Seminara - "Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos", NeurIPS 2024 (link).
Michele Mazzamuto - "Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activities", CVPR 2025 (link).
Chiara Plizzari- "Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos", CVPR 2025 (link).
Rosario Leonardi - "Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection?", ECCV 2024 (link).
15.50 - 16.20 Coffee break ☕
16.20 - 17.00 Session 5: Multimodal learning
Davide Talon - "Seeing the Abstract: Translating the Abstract Language for Vision Language Models", CVPR 2025 (link).
Claudia Cuttano - "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation", CVPR 2025 (link).
Lorenzo Vaquero - "Superpowering Open-Vocabulary Object Detectors for X-ray Vision", ICCV 2025 (link).
Fabrizio Guillaro - "A Bias-Free Training Paradigm for More General AI-generated Image Detection", CVPR 2025 (link).
17.00 - 17.20 Closing remarks
Keynote Speakers:
Keynote Speakers:
Fabio Cermelli
Fabio Cermelli
FocoosAI
FocoosAI
Vicky Kalogeiton
Vicky Kalogeiton
École Polytechnique
École Polytechnique
Giovanni Maria Farinella
Giovanni Maria Farinella
University of Catania
University of Catania
Organizers:
Organizers:
Massimiliano
Mancini
Massimiliano
Mancini
University of Trento
University of Trento
Andrea
Pilzer
Andrea
Pilzer
NVIDIA
NVIDIA
Nicu
Sebe
Nicu
Sebe
University of Trento
University of Trento
We hope to see you there!
We hope to see you there!
Page updated
Google Sites
Report abuse