@article{forte2026egostream,
  title={EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision},
  author={Forte, Rosario and Lando, Giuseppe and Furnari, Antonino},
  journal={arXiv preprint arXiv:2605.31557},
  year={2026}
}

                              

                                @article{santosvillafranca2026egometas,
  title={Ego-METAS: an Egocentric online Multimodal Energy-efficient Temporal Action Segmentation benchmark},
  author={Santos-Villafranca, Maria and Bermudez-Cameo, Jesus and Perez-Yus, Alejandro and Farinella, Giovanni Maria and Furnari, Antonino},
  journal={arXiv preprint},
  year={2026},
  arxiv={2606.02246}
}

                              

                                @article{seminara2026recipe,
  title={RECIPE: Procedural Planning via Grounding in Instructional Video},
  author={Seminara, Luigi and Furnari, Antonino and Torresani, Lorenzo},
  journal={arXiv preprint arXiv:2605.19976},
  year={2026}
}

                              

                                @inproceedings{Seminara2026ViterbiPlanNet,
  year = { 2026 },
  booktitle = { IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) },
  title = { ViterbiPlanNet: Injecting Procedural Knowledge via Differentiable Viterbi for Planning in Instructional Videos },
  author = { Luigi Seminara and Davide Moltisanti and Antonino Furnari },
  pdf = {https://arxiv.org/pdf/2603.04265},
  url = {https://arxiv.org/abs/2603.04265}
}

                              

                                @article{seminara2026task,
  author={Seminara, Luigi and Farinella, Giovanni Maria and Furnari, Antonino},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  title={Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos}, 
  year={2026},
  volume={},
  number={},
  pages={1-18},
  doi={10.1109/TPAMI.2026.3689721}}

                              

                                @article{Plini2026TI-PREGO,
  author = { Leonardo Plini and Luca Scofano and Edoardo De Matteis and Guido Maria D’Amely di Melendugno and Alessandro Flaborea and Andrea Sanchietti and Giovanni Maria Farinella and Fabio Galasso and Antonino Furnari },
  journal = { Computer Vision and Image Understanding },
  title = { TI-PREGO: Chain of Thought and In-Context Learning for online mistake detection in PRocedural EGOcentric videos },
  year = { 2026 },
  url = { https://www.sciencedirect.com/science/article/pii/S1077314225003364 },
  pdf = { publications/Plini2026TIPREGO.pdf },
  doi = { https://doi.org/10.1016/j.cviu.2025.104613 },
  pages = {  },
}

                              

                                @article{MurLabadia2026-Integrating,
  pdf = { publications/Mur_Labadia2026Integrating.pdf },
  url = { https://ieeexplore.ieee.org/document/11344783 },
  pages = { 1-17 },
  number = {  },
  year = { 2026 },
  doi = { http://10.1109/TPAMI.2026.3652831 },
  title = { Integrating Affordances and Attention models for Short-Term Object Interaction Anticipation },
  journal = { IEEE Transactions on Pattern Analysis and Machine Intelligence },
  author = { Lorenzo Mur-Labadia and Ruben Martinez-Cantin and Jose J. Guerrero and Giovanni Maria Farinella and Antonino Furnari },
}

                              

                                @inproceedings{Ragusa2026Ego-EXTRA,
  year = { 2026 },
  booktitle = { IEEE Winter Conference on Application of Computer Vision (WACV) },
  title = { Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance },
  author = { Francesco Ragusa and Michele Mazzamuto and Rosario Forte and Irene D'Ambra and James Fort and Jakob Engel and Antonino Furnari and Giovanni Maria Farinella },
  pdf = { https://arxiv.org/pdf/2512.13238 },
}

                              

                                @inproceedings{Manigrasso2026Online,
  year = { 2026 },
  booktitle = { IEEE Winter Conference on Application of Computer Vision (WACV) },
  title = { Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory },
  author = { Zaira Manigrasso and Matteo Dunnhofer and Antonino Furnari and Moritz Nottebaum and Antonio Finocchiaro and Davide Marana and Rosario Forte and Giovanni Maria Farinella and Christian Micheloni },
  pdf = {  },
}

                              

                                @inproceedings{forte2026exploring,
  title={Exploring Multimodal LMMs for Online Episodic Memory Question Answering on the Edge},
  author={Giuseppe Lando and Rosario Forte and Antonino Furnari},
  booktitle={International Conference on Computer Vision Theory and Applications (VISAPP)},
  year={2026},
  url={https://arxiv.org/abs/2602.22455},
  pdf={https://arxiv.org/pdf/2602.22455}
}

                              

                                @article{testa2026slu2k,
  title={SLU-2K: A Question-Based Benchmark for Semantic Evaluation of Sign Language Translation},
  author={Testa, Zeno and Furnari, Antonino and Baraldi, Lorenzo and D\'iaz-Rodr\'iguez, Natalia},
  journal={arXiv preprint arXiv:2606.03788},
  year={2026},
  arxiv={2606.03788}
}

                              

                                @article{Grauman2025,
  author    = {Kristen Grauman and Andrew Westbury and Lorenzo Torresani and Kris Kitani and Jitendra Malik and Triantafyllos Afouras and Kumar Ashutosh and Vijay Baiyya and Siddhant Bansal and Bikram Boote and Eugene Byrne and Zach Chavis and Joya Chen and Feng Cheng and Fu-Jen Chu and Sean Crane and Avijit Dasgupta and Jing Dong and Maria Escobar and Cristhian Forigua and Abrham Gebreselasie and Sanjay Haresh and Jing Huang and Md Mohaiminul Islam and Suyog Jain and Rawal Khirodkar and Devansh Kukreja and Kevin J. Liang and Jia-Wei Liu and Sagnik Majumder and Yongsen Mao and Miguel Martin and Effrosyni Mavroudi and Tushar Nagarajan and Francesco Ragusa and Santhosh Kumar Ramakrishnan and Luigi Seminara and Arjun Somayazulu and Yale Song and Shan Su and Zihui Xue and Edward Zhang and Jinxu Zhang and Angela Castillo and Changan Chen and Xinzhu Fu and Ryosuke Furuta and Cristina González and Prince Gupta and Jiabo Hu and Yifei Huang and Yiming Huang and Weslie Khoo and Anush Kumar and Robert Kuo and Sach Lakhavani and Miao Liu and Mi Luo and Zhengyi Luo and Brighid Meredith and Austin Miller and Oluwatumininu Oguntola and Xiaqing Pan and Penny Peng and Shraman Pramanick and Merey Ramazanova and Fiona Ryan and Wei Shan and Kiran Somasundaram and Chenan Song and Audrey Southerland and Masatoshi Tateno and Huiyu Wang and Yuchen Wang and Takuma Yagi and Mingfei Yan and Xitong Yang and Zecheng Yu and Shengxin Cindy Zha and Chen Zhao and Ziwei Zhao and Zhifan Zhu and Jeff Zhuo and Pablo Arbeláez and Gedas Bertasius and David Crandall and Dima Damen and Jakob Engel and Giovanni Maria Farinella and Antonino Furnari and Bernard Ghanem and Judy Hoffman and C. V. Jawahar and Richard Newcombe and Hyun Soo Park and James M. Rehg and Yoichi Sato and Manolis Savva and Jianbo Shi and Mike Zheng Shou and Michael Wray},
  title     = {Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives},
  journal   = {International Journal of Computer Vision},
  year      = {2025},
  month     = nov,
  day       = {24},
  volume    = {},
  number    = {},
  pages     = {},
  doi       = {10.1007/s11263-025-02557-6},
  url       = {https://doi.org/10.1007/s11263-025-02557-6},
  issn      = {1573-1405},
  pdf = {https://link.springer.com/content/pdf/10.1007/s11263-025-02557-6.pdf}
}

                              

                                @article{quattrocchi2024synchronization,
  year = { 2025 },
  journal = { International Journal on Computer Vision (IJCV) },
  title = { Exocentric-to-Egocentric Adaptation for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs },
  author = { Camillo Quattrocchi and Antonino Furnari and Daniele Di Mauro and Mario Valerio Giuffrida and Giovanni Maria Farinella },
  url = { https://github.com/fpv-iplab/synchronization-is-all-you-need },
}

                              

                                @inproceedings{Rodin2025EASG-Bench,
  year = { 2025 },
  booktitle = { IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) },
  title = { EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs },
  author = { Ivan Rodin and Tz-Ying Wu and Kyle Min and Sharath Nittur Sridhar and Antonino Furnari and Subarna Tripathi and Giovanni Maria Farinella },
  url = { https://arxiv.org/abs/2506.05787 },
  pdf = { https://arxiv.org/pdf/2506.05787.pdf },
}

                              

                                @inproceedings{Lando2025HowFar,
  author    = {Giuseppe Lando and Rosario Forte and Giovanni Maria Farinella and Antonino Furnari},
  title     = {How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?},
  booktitle = {Proceedings of the 23rd International Conference on Image Analysis and Processing (ICIAP)},
  year      = {2025}
}

                              

                                @article{Plizzari2024AnOutlook,
  author = { Chiara Plizzari and Gabriele Goletto and Antonino Furnari and Siddhant Bansal and Francesco Ragusa and Giovanni Maria Farinella and Dima Damen and Tatiana Tommasi },
  journal = {  International Journal of Computer Vision (IJCV)  },
  title = {  An Outlook into the Future of Egocentric Vision  },
  year = {2024},
  pdf = {https://link.springer.com/content/pdf/10.1007/s11263-024-02095-7.pdf}
}

                              

                                @inproceedings{rodin2023action,
  primaryclass = { cs.CV },
  archiveprefix = { arXiv },
  eprint = { 2312.03391 },
  pdf = {https://arxiv.org/pdf/2312.03391.pdf},
  year = {2024},
  booktitle = {  Conference on Computer Vision and Pattern Recognition (CVPR)  },
  title = {Action Scene Graphs for Long-Form Understanding of Egocentric Videos},
  author = {Ivan Rodin and Antonino Furnari and Kyle Min and Subarna Tripathi and Giovanni Maria Farinella}
}

                              

                                @inproceedings{mur-labadia2024AFF-ttention,
  pdf = {https://arxiv.org/pdf/2406.01194.pdf},
  year = {2024},
  booktitle = { European Conference on Computer Vision (ECCV) },
  title = { AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation },
  author = { Lorenzo Mur-Labadia and Ruben Martinez-Cantin and Josechu Guerrero and Giovanni Maria Farinella and Antonino Furnari },
}

                              

                                @inproceedings{seminara2024differentiable,
 author = {Seminara, Luigi and Farinella, Giovanni Maria and Furnari, Antonino},
 booktitle = {Advances in Neural Information Processing Systems},
 title = {Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos},
 pdf = {https://arxiv.org/pdf/2406.01486.pdf},
 url = {https://github.com/fpv-iplab/Differentiable-Task-Graph-Learning},
 year = {2024}
}

                              

                                @inproceedings{grauman2023egoexo4d,
  primaryclass = { cs.CV },
  archiveprefix = { arXiv },
  eprint = { 2311.18259 },
  pdf = {https://arxiv.org/pdf/2311.18259.pdf},
  url = {https://ego-exo4d-data.org/},
  year = {2024},
  booktitle = {  Conference on Computer Vision and Pattern Recognition (CVPR)  },
  title = { Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives },
  author = { Kristen Grauman and Andrew Westbury and Lorenzo Torresani and Kris Kitani and Jitendra Malik and Triantafyllos Afouras and Kumar Ashutosh and Vijay Baiyya and Siddhant Bansal and Bikram Boote and Eugene Byrne and Zach Chavis and Joya Chen and Feng Cheng and Fu-Jen Chu and Sean Crane and Avijit Dasgupta and Jing Dong and Maria Escobar and Cristhian Forigua and Abrham Gebreselasie and Sanjay Haresh and Jing Huang and Md Mohaiminul Islam and Suyog Jain and Rawal Khirodkar and Devansh Kukreja and Kevin J Liang and Jia-Wei Liu and Sagnik Majumder and Yongsen Mao and Miguel Martin and Effrosyni Mavroudi and Tushar Nagarajan and Francesco Ragusa and Santhosh Kumar Ramakrishnan and Luigi Seminara and Arjun Somayazulu and Yale Song and Shan Su and Zihui Xue and Edward Zhang and Jinxu Zhang and Angela Castillo and Changan Chen and Xinzhu Fu and Ryosuke Furuta and Cristina Gonzalez and Prince Gupta and Jiabo Hu and Yifei Huang and Yiming Huang and Weslie Khoo and Anush Kumar and Robert Kuo and Sach Lakhavani and Miao Liu and Mi Luo and Zhengyi Luo and Brighid Meredith and Austin Miller and Oluwatumininu Oguntola and Xiaqing Pan and Penny Peng and Shraman Pramanick and Merey Ramazanova and Fiona Ryan and Wei Shan and Kiran Somasundaram and Chenan Song and Audrey Southerland and Masatoshi Tateno and Huiyu Wang and Yuchen Wang and Takuma Yagi and Mingfei Yan and Xitong Yang and Zecheng Yu and Shengxin Cindy Zha and Chen Zhao and Ziwei Zhao and Zhifan Zhu and Jeff Zhuo and Pablo Arbelaez and Gedas Bertasius and David Crandall and Dima Damen and Jakob Engel and Giovanni Maria Farinella and Antonino Furnari and Bernard Ghanem and Judy Hoffman and C. V. Jawahar and Richard Newcombe and Hyun Soo Park and James M. Rehg and Yoichi Sato and Manolis Savva and Jianbo Shi and Mike Zheng Shou and Michael Wray },
}

                              

                                @inproceedings{flaborea2024PREGO,
  year = {2024},
  booktitle = {  Conference on Computer Vision and Pattern Recognition (CVPR)  },
  title = {  PREGO: online mistake detection in PRocedural EGOcentric videos  },
  author = { Alessandro Flaborea and Guido D'Amely and Leonardo Plini and Luca Scofano and Edoardo De Matteis and Antonino Furnari and Giovanni Maria Farinella and Fabio Galasso },
  pdf={https://arxiv.org/pdf/2404.01933},
  url={https://github.com/aleflabo/PREGO?tab=readme-ov-file}

}

                              

                                @inproceedings{quattrocchi2024synchronization,
  pdf = {https://arxiv.org/pdf/2312.02638.pdf},
  year = {2024},
  booktitle = { European Conference on Computer Vision (ECCV) },
  title = { Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs },
  author = { Camillo Quattrocchi and Antonino Furnari and Daniele Di Mauro and Mario Valerio Giuffrida and Giovanni Maria Farinella },
  url = {https://github.com/fpv-iplab/synchronization-is-all-you-need}
}