Visual Intelligence for
Human-AI Collaboration

Our papers “Differentiable Task Graph Learning” (NeurIPS 2024) and “Ego-Exo4D” (CVPR 2024) have received the EgoVis Distinguished Paper Award 2024/2025, announced at the EgoVis Workshop at CVPR 2026. Big congrats to Luigi Seminara and all co-authors!

🏆 Distinguished Paper

Differentiable Task Graph Learning

Luigi Seminara, Giovanni Maria Farinella, Antonino Furnari

🏆 Distinguished Paper

Ego-Exo4D: Understanding Skilled Human Activity

Kristen Grauman, Andrew Westbury, Lorenzo Torresani, Kris Kitani, Jitendra Malik, Triantafyllos Afouras, Kumar Ashutosh, Vijay Baiyya, Siddhant Bansal, Bikram Boote, Eugene Byrne, Zach Chavis, Joya Chen, Feng Cheng, Fu-Jen Chu, Sean Crane, Avijit Dasgupta, Jing Dong, Maria Escobar, Cristhian Forigua, Abrham Gebreselasie, Sanjay Haresh, Jing Huang, Md Mohaiminul Islam, Suyog Jain, Rawal Khirodkar, Devansh Kukreja, Kevin J Liang, Jia-Wei Liu, Sagnik Majumder, Yongsen Mao, Miguel Martin, Effrosyni Mavroudi, Tushar Nagarajan, Francesco Ragusa, Santhosh Kumar Ramakrishnan, Luigi Seminara, Arjun Somayazulu, Yale Song, Shan Su, Zihui Xue, Edward Zhang, Jinxu Zhang, Angela Castillo, Changan Chen, Xinzhu Fu, Ryosuke Furuta, Cristina Gonzalez, Prince Gupta, Jiabo Hu, Yifei Huang, Yiming Huang, Weslie Khoo, Anush Kumar, Robert Kuo, Sach Lakhavani, Miao Liu, Mi Luo, Zhengyi Luo, Brighid Meredith, Austin Miller, Oluwatumininu Oguntola, Xiaqing Pan, Penny Peng, Shraman Pramanick, Merey Ramazanova, Fiona Ryan, Wei Shan, Kiran Somasundaram, Chenan Song, Audrey Southerland, Masatoshi Tateno, Huiyu Wang, Yuchen Wang, Takuma Yagi, Mingfei Yan, Xitong Yang, Zecheng Yu, Shengxin Cindy Zha, Chen Zhao, Ziwei Zhao, Zhifan Zhu, Jeff Zhuo, Pablo Arbelaez, Gedas Bertasius, David Crandall, Dima Damen, Jakob Engel, Giovanni Maria Farinella, Antonino Furnari, Bernard Ghanem, Judy Hoffman, C. V. Jawahar, Richard Newcombe, Hyun Soo Park, James M. Rehg, Yoichi Sato, Manolis Savva, Jianbo Shi, Mike Zheng Shou, Michael Wray

Three new preprints are now available on arXiv:

• R. Forte, G. Lando, A. Furnari. EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision. [arXiv]
• M. Santos-Villafranca, J. Bermudez-Cameo, A. Perez-Yus, G. M. Farinella, A. Furnari. Ego-METAS: an Egocentric online Multimodal Energy-efficient Temporal Action Segmentation benchmark. [arXiv] [Website]
• L. Seminara, A. Furnari, L. Torresani. RECIPE: Procedural Planning via Grounding in Instructional Video. [arXiv]

Our paper Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos has been accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

Our paper “Integrating Affordances and Attention models for Short-Term Object Interaction Anticipation” has been accepted to the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)!

The preprint is available on arXiv.

One paper accepted at CVPR 2026!

• L. Seminara, D. Moltisanti, A. Furnari. ViterbiPlanNet: Injecting Procedural Knowledge via Differentiable Viterbi for Planning in Instructional Videos. [Paper]

Our paper “How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?” by Giuseppe Lando, Rosario Forte, Giovanni Maria Farinella, and Antonino Furnari, has been awarded the best student paper award at the 23rd International Conference on Image Analysis and Processing (ICIAP 2025).

Three papers accepted for publication at the IEEE Winter Conference on Applications of Computer Vision (WACV) 2026:

• Zaira Manigrasso, Matteo Dunnhofer, Antonino Furnari, Moritz Nottebaum, Antonio Finocchiaro, Davide Marana, Rosario Forte, Giovanni Maria Farinella, Christian Micheloni (2026). Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory. In IEEE Winter Conference on Applications of Computer Vision (WACV).
• Michele Mazzamuto, Daniele Di Mauro, Gianpiero Francesca, Giovanni Maria Farinella, Antonino Furnari (2026). ProSkill: Segment-Level Skill Assessment in Procedural Videos. In IEEE Winter Conference on Applications of Computer Vision (WACV).
• Francesco Ragusa, Michele Mazzamuto, Rosario Forte, Irene D'Ambra, James Fort, Jakob Engel, Antonino Furnari, Giovanni Maria Farinella (2026). Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance. In IEEE Winter Conference on Applications of Computer Vision (WACV).

7 papers accepted at the 23rd International Conference on Image Analysis and Processing (ICIAP 2025)!

Of these, 3 have been accepted for oral presentation, 2 as posters, and 2 in the workshops.

Oral Presentations:

• Catinello, A. S., Farinella, G. M., & Furnari, A. (2025). Mamba-OTR: a Mamba-based Solution for Online Take and Release Detection from Untrimmed Egocentric Video.
• Finocchiaro, A., Farinella, G. M., & Furnari, A. (2025). Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation.
• Lando, G., Forte, R., Farinella, G. M., & Furnari, A. (2025). How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?

Poster Presentations:

• Catinello, A. S., Dunnhofer, M., Farinella, G. M., Frontoni, E., Furnari, A., Micheloni, C., Paolanti, M., Pietrini, R., Salierno, D., Stacchio, L., & Yaar, A. (2025). Ego and exo views for an object-level human behavior analysis and understanding through tracking in retail spaces.
• Manigrasso, Z., Finocchiaro, A., Manara, D., Forte, R., Nottebaum, M., Dunnhofer, M., Farinella, G. M., Furnari, A., & Micheloni, C. (2025). T-EVO: Tracking in Egovision for Online Visual Episodic Memory.

Workshop Papers:

• Yaar, A., Rodin, I., Farinella, G. M., & Furnari, A. (2025). A Benchmark of Egocentric Scene Graph Prediction Methods for Understanding Human-Object Interactions.
• Finocchiaro, A., Catinello, A. S., Mazzamuto, M., Leonardi, R., Furnari, A., & Farinella, G. M. (2025). A Real-Time System for Egocentric Hand-Object Interaction Detection in Industrial Domains.

Full program here.

One paper accepted at CVPR 2025!:

• Michele Mazzamuto, Antonino Furnari, Yoichi Sato, Giovanni Maria Farinella. Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activities. [Paper]

Our paper on differentiable task graphs has been accepted at NeurIPS 2024 as a spotlight!

Luigi Seminara, Giovanni Maria Farinella, Antonino Furnari Furnari (2024). Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos. In Advances in Neural Information Processing Systems. [paper] [code]

Three papers accepted at ECCV 2024!

• Lorenzo Mur-Labadia, Ruben Martinez-Cantin, Josechu Guerrero, Giovanni Maria Farinella, Antonino Furnari. AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation. [Paper]
• Camillo Quattrocchi, Antonino Furnari, Daniele Di Mauro, Mario Valerio Giuffrida, Giovanni Maria Farinella. Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs. [Paper]
• Rosario Leonardi, Antonino Furnari, Francesco Ragusa, Giovanni Maria Farinella. Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection? [Paper]

We are among winners of two challenges at the EgoVis workshop:

• 🥇 1st place at the EgoVis HoloLens Mistake Detection Challenge with a solution based on gaze analysis detailed here.
• 🥈 2nd place at the EgoVis Ego4D Short Term Anticipation Challenge with a solution based on the paper \"AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation\" in collaboration with Univ. Zaragoza.

Three papers accepted at CVPR 2024! (1 oral + 2 posters):

• Alessandro Flaborea, Guido Maria D'Amely di Melendugno, Leonardo Plini, Luca Scofano, Edoardo De Matteis, Antonino Furnari, Giovanni Maria Farinella, Fabio Galasso. PREGO: online mistake detection in PRocedural EGOcentric videos [Paper]
• Ivan Rodin, Antonino Furnari, Kyle Min, Subarna Tripathi, Giovanni Maria Farinella. Action Scene Graphs for Long-Form Understanding of Egocentric Videos. [Paper]
• Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives. With other 100 authors! Oral < 1% accept rate. [Paper]

Survey paper An Outlook into the Future of Egocentric Vision is open for comments on OpenReview until 15 Sep.

PNRR PRIN Project “TEAM” has been accepted and will be funded by the Italian ministry of University and Research.

PRIN Project “EXTRA-EYE” has been accepted and will be funded by the Italian ministry of University and Research.