Chiara Plizzari

Chiara Plizzari

Hello! I’m Chiara and I am an Assistant Professor at Bocconi University, in the Department of Computing Sciences, where I lead the Vision and Video Understanding group. Previously, I was a Postdoctoral Researcher at the Smart Eyewear Lab, a joint research center between EssilorLuxottica and Politecnico di Milano, in the group of Prof. Matteo Matteucci. Prior to that, I was a Student Researcher at Google Research in Zurich, where I worked on multi-modal LLMs for video understanding in Federico Tombari’s team. I did my PhD in the VANDAL (Visual AND Multimodal Applied Learning) laboratory at Politecnico di Torino, supervised by Prof. Barbara Caputo, as an ELLIS PhD student co-supervised by Prof. Dima Damen (University of Bristol). During my PhD I visited the University of Bristol and the Berkeley AI Research Lab (BAIR), collaborating with Prof. Angjoo Kanazawa.

I am interested in video understanding and egocentric vision, and intrigued by how vision can be complemented by multiple modalities, including language, audio, and 3D information, towards 4D scene understanding.

News

Jul 2026 I gave an invited research seminar at Microsoft Research Zurich, in Prof. Marc Pollefeys’ group.
May 2026 I gave an invited talk and served as Local Chair at the 8th International Workshop on Computer Vision (IWCV 2026) in Stresa, Italy.
2026 I was awarded a TEF Research Fellowship as PI for E4RL: Egocentric 4D Representations for Robot Learning, with scientific collaborators Francis Engelmann (USI) and Antonio Loquercio (University of Pennsylvania)!
2026 Our PRIN Research Grant PREMISE: Predictive Multimodal Intelligence with Spatial and Episodic Memory was funded! I am a collaborator (project coordinator: Lorenzo Baraldi; unit PI: Federica Arrigoni).
Dec 2025 I received a Bocconi Junior Researchers’ Grant and two CINECA ISCRA-C computational grants (EgoWorld and SQu4D) as PI.
Nov 2025 I gave an invited talk, On the Challenges of Learning from Videos, at BNAIC 2025 in Namur, Belgium.
Sep 2025 I received the AIxIA Award for Best PhD Thesis (“Marco Cadoli” Prize)! 🏆
Sep 2025 I joined Bocconi University as an Assistant Professor, where I lead the Vision and Video Understanding group!
Jun 2025 Our team won first place in the HD-EPIC VQA Challenge at CVPR 2025! 🥇
Mar 2025 Happy to announce that the work I did during my research time at Google has been accepted to CVPR2025! :sparkles:
Jan 2025 I started as a Postdoctoral Researcher at the Smart Eyewear Lab (Politecnico di Milano), in the group of Prof. Matteo Matteucci.
Sep 2024 I received the Best PhD Award from Politecnico di Torino (36th doctoral cycle)!
Apr 2024 I just started as a Student Researcher in Google Zurich in Federico Tombari’s team!
Oct 2023 I gave a talk on Cross-Domain Egocentric Vision at I-RIM 2023!
Oct 2023 Honored to be part of the organization of the Women in Computer Vision Workshop (WiCV) @ ICCV23!
Oct 2023 Excited to be selected for the Doctoral Consortium @ ICCV23!
Jun 2023 Our work on Mixed Sequence Predictions won the 2nd place at the EPIC-Kitchens Unsupervised Domain Adaptation Challenge at CVPR! 🥈
Feb 2023 I visited Berkeley Artificial Intelligence Research (BAIR) Lab and started a collaboration with Prof. Angjoo Kanazawa! :bear:

me_bair
Apr 2022 I gave a talk on Cross-Domain Activity Recognition at University of Bristol to the Machine Learning and Computer Vision group!
Mar 2022 Started a 9-months research visiting @ University of Bristol with Prof. Dima Damen :sparkles: :smile:

me_bair
Jun 2021 Our work on Relative Norm Alignment won the 3rd place at the EPIC-Kitchens Unsupervised Domain Adaptation Challenge at CVPR! 🥉

Selected Publications Full list

  1. Topology-Aware 4D Gaussian Splatting for Egocentric Videos
    L. Vanni, Stefano Gasperini, Federico Tombari, Chiara Plizzari
    arXiv preprint arXiv:2611.16012, 2026.
    @article{vanni2026topology,
      title = {Topology-Aware 4D Gaussian Splatting for Egocentric Videos},
      author = {Vanni, L. and Gasperini, Stefano and Tombari, Federico and Plizzari, Chiara},
      journal = {arXiv preprint arXiv:2611.16012},
      year = {2026}
    }
  2. Long Time No See: Benchmarking VLMs for Out-of-Sight Spatiotemporal Reasoning in Egocentric Videos
    F. Ma, I. A. Ban, E. Homburg, Gabriele Goletto, R. Pautrat, M. Rad, Chiara Plizzari, Marc Pollefeys
    arXiv preprint arXiv:2609.34630, 2026.
    @article{ma2026longtime,
      title = {Long Time No See: Benchmarking VLMs for Out-of-Sight Spatiotemporal Reasoning in Egocentric Videos},
      author = {Ma, F. and Ban, I. A. and Homburg, E. and Goletto, Gabriele and Pautrat, R. and Rad, M. and Plizzari, Chiara and Pollefeys, Marc},
      journal = {arXiv preprint arXiv:2609.34630},
      year = {2026}
    }
  3. Scene Graphs for Preserving Compositional Semantics in Text-to-Image Reinforcement Learning
    U. Bahçıvanoğlu, G. Ceria, F. Pezzoli, Luca Biggio, Chiara Plizzari, R. Barbano
    Advances in Neural Information Processing Systems Workshops (NeurIPS Workshops), 2026.
    @inproceedings{bahcivanoglu2026scenegraphs,
      title = {Scene Graphs for Preserving Compositional Semantics in Text-to-Image Reinforcement Learning},
      author = {Bah{\c{c}}{\i}vano{\u{g}}lu, U. and Ceria, G. and Pezzoli, F. and Biggio, Luca and Plizzari, Chiara and Barbano, R.},
      booktitle = {Advances in Neural Information Processing Systems Workshops (NeurIPS Workshops)},
      year = {2026}
    }
  4. A Framework for Talk-To-Me Detection and Human Action Recognition on Smart Eyewear
    H. Quan, G. Corti, S. Pidò, P. Bartoli, Chiara Plizzari, A. Giudici, Francesca Palermo, Matteo Matteucci, Simone Mentasti
    Neural Computing and Applications, 2026.
    @article{quan2026talktome,
      title = {A Framework for Talk-To-Me Detection and Human Action Recognition on Smart Eyewear},
      author = {Quan, H. and Corti, G. and Pid{\`o}, S. and Bartoli, P. and Plizzari, Chiara and Giudici, A. and Palermo, Francesca and Matteucci, Matteo and Mentasti, Simone},
      journal = {Neural Computing and Applications},
      year = {2026}
    }
  5. Graph it First! Enabling Reasoning on Long-form Egocentric Videos through Scene Graphs
    Agnese Taluzzi, Riccardo Santambrogio, Simone Mentasti, Chiara Plizzari, Matteo Matteucci
    European Conference on Computer Vision Workshops (ECCV Workshops), 2026.
    @inproceedings{taluzzi2026graphitfirst,
      title = {Graph it First! Enabling Reasoning on Long-form Egocentric Videos through Scene Graphs},
      author = {Taluzzi, Agnese and Santambrogio, Riccardo and Mentasti, Simone and Plizzari, Chiara and Matteucci, Matteo},
      booktitle = {European Conference on Computer Vision Workshops (ECCV Workshops)},
      year = {2026}
    }
  6. EgoAfford: Affordance-aware Zero-Shot Open-Vocabulary Egocentric Action Recognition
    Daniele Gesualdi, Riccardo Santambrogio, Francesca Palermo, Chiara Plizzari, Simone Mentasti, Matteo Matteucci
    International Conference on Pattern Recognition (ICPR), 2026.
    @inproceedings{gesualdi2026egoafford,
      title = {EgoAfford: Affordance-aware Zero-Shot Open-Vocabulary Egocentric Action Recognition},
      author = {Gesualdi, Daniele and Santambrogio, Riccardo and Palermo, Francesca and Plizzari, Chiara and Mentasti, Simone and Matteucci, Matteo},
      booktitle = {International Conference on Pattern Recognition (ICPR)},
      year = {2026}
    }
  7. Continuous Online Action Detection from Egocentric Videos
    Riccardo Santambrogio, Chiara Plizzari, Francesca Palermo, Simone Mentasti, Matteo Matteucci
    International Conference on Pattern Recognition (ICPR), 2026.
    @inproceedings{santambrogio2026continuous,
      title = {Continuous Online Action Detection from Egocentric Videos},
      author = {Santambrogio, Riccardo and Plizzari, Chiara and Palermo, Francesca and Mentasti, Simone and Matteucci, Matteo},
      booktitle = {International Conference on Pattern Recognition (ICPR)},
      year = {2026}
    }
  8. Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos
    Chiara Plizzari, Alessio Tonioni, Yongqin Xian, Achin Kulshrestha, Federico Tombari
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
    @inproceedings{plizzari2025egotempo,
      title = {Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos},
      author = {Plizzari, Chiara and Tonioni, Alessio and Xian, Yongqin and Kulshrestha, Achin and Tombari, Federico},
      booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      year = {2025}
    }
  9. Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind
    Chiara Plizzari, Shubham Goel, Toby Perrett, Jacob Chalk, Angjoo Kanazawa, Dima Damen
    International Conference on 3D Vision (3DV), 2025.
    @inproceedings{plizzari2025spatial,
      title = {Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind},
      author = {Plizzari, Chiara and Goel, Shubham and Perrett, Toby and Chalk, Jacob and Kanazawa, Angjoo and Damen, Dima},
      booktitle = {International Conference on 3D Vision (3DV)},
      year = {2025}
    }
  10. From Pixels to Graphs: Using Scene and Knowledge Graphs for HD-EPIC VQA Challenge
    Agnese Taluzzi, Daniele Gesualdi, Riccardo Santambrogio, Chiara Plizzari, Francesca Palermo, Simone Mentasti, Matteo Matteucci
    HD-EPIC VQA Challenge @ CVPR, 2025.
    1st Place
    @inproceedings{taluzzi2025pixels,
      title = {From Pixels to Graphs: Using Scene and Knowledge Graphs for HD-EPIC VQA Challenge},
      author = {Taluzzi, Agnese and Gesualdi, Daniele and Santambrogio, Riccardo and Plizzari, Chiara and Palermo, Francesca and Mentasti, Simone and Matteucci, Matteo},
      booktitle = {HD-EPIC VQA Challenge @ CVPR},
      year = {2025}
    }
  11. Relative Norm Alignment for Tackling Domain Shift in Deep Multi-modal Classification
    Mirco Planamente, Chiara Plizzari, Simone Alberto Peirone, Barbara Caputo, Andrea Bottino
    International Journal of Computer Vision (IJCV), 2024.
    @article{planamente2024relative,
      title = {Relative Norm Alignment for Tackling Domain Shift in Deep Multi-modal Classification},
      author = {Planamente, Mirco and Plizzari, Chiara and Peirone, Simone Alberto and Caputo, Barbara and Bottino, Andrea},
      journal = {International Journal of Computer Vision (IJCV)},
      year = {2024}
    }
  12. An Outlook into the Future of Egocentric Vision
    Chiara Plizzari*, Gabriele Goletto*, Antonino Furnari*, Siddhant Bansal*, Francesco Ragusa*, Giovanni Maria Farinella, Dima Damen, Tatiana Tommasi
    International Journal of Computer Vision (IJCV), 2024.
    @article{plizzari2024outlook,
      title = {An Outlook into the Future of Egocentric Vision},
      author = {Plizzari*, Chiara and Goletto*, Gabriele and Furnari*, Antonino and Bansal*, Siddhant and Ragusa*, Francesco and Farinella, Giovanni Maria and Damen, Dima and Tommasi, Tatiana},
      journal = {International Journal of Computer Vision (IJCV)},
      year = {2024}
    }
  13. What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations
    Chiara Plizzari, Toby Perrett, Barbara Caputo, Dima Damen
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
    @inproceedings{plizzari2023cook,
      title = {What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations},
      author = {Plizzari, Chiara and Perrett, Toby and Caputo, Barbara and Damen, Dima},
      booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
      year = {2023}
    }
  14. EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge: Mixed Sequences Prediction
    Amirshayan Nasirimajd, Simone Alberto Peirone, Chiara Plizzari, Barbara Caputo
    EPIC Workshop @ CVPR, 2023.
    2nd Place
    @inproceedings{nasirimajd2023epickitchens100,
      title = {EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge: Mixed Sequences Prediction},
      author = {Nasirimajd, Amirshayan and Peirone, Simone Alberto and Plizzari, Chiara and Caputo, Barbara},
      booktitle = {EPIC Workshop @ CVPR},
      year = {2023}
    }
  15. E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition
    Chiara Plizzari*, Mirco Planamente*, Gabriele Goletto, Marco Cannici, Emanuele Gusso, Matteo Matteucci, Barbara Caputo
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
    @inproceedings{plizzari2022e2,
      title = {E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition},
      author = {Plizzari*, Chiara and Planamente*, Mirco and Goletto, Gabriele and Cannici, Marco and Gusso, Emanuele and Matteucci, Matteo and Caputo, Barbara},
      booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      pages = {19935--19947},
      year = {2022}
    }
  16. Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition
    Mirco Planamente*, Chiara Plizzari*, Emanuele Alberti, Barbara Caputo
    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022.
    @inproceedings{planamente2022domain,
      title = {Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition},
      author = {Planamente*, Mirco and Plizzari*, Chiara and Alberti, Emanuele and Caputo, Barbara},
      booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
      pages = {1807--1818},
      year = {2022}
    }
  17. DA4Event: Towards Bridging the Sim-to-Real Gap for Event Cameras Using Domain Adaptation
    Mirco Planamente*, Chiara Plizzari*, Marco Cannici*, Marco Ciccone, Francesco Strada, Andrea Bottino, Matteo Matteucci, Barbara Caputo
    IEEE Robotics and Automation Letters (RA-L), presented at IROS 2021, 2021.
    @article{planamente2021da4event,
      title = {DA4Event: Towards Bridging the Sim-to-Real Gap for Event Cameras Using Domain Adaptation},
      author = {Planamente*, Mirco and Plizzari*, Chiara and Cannici*, Marco and Ciccone, Marco and Strada, Francesco and Bottino, Andrea and Matteucci, Matteo and Caputo, Barbara},
      journal = {IEEE Robotics and Automation Letters (RA-L), presented at IROS 2021},
      volume = {6},
      number = {4},
      pages = {6616--6623},
      year = {2021},
      publisher = {IEEE}
    }
  18. Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
    Chiara Plizzari, Marco Cannici, Matteo Matteucci
    Computer Vision and Image Understanding (CVIU), 2021.
    @article{plizzari2021skeleton,
      title = {Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks},
      author = {Plizzari, Chiara and Cannici, Marco and Matteucci, Matteo},
      journal = {Computer Vision and Image Understanding (CVIU)},
      volume = {208},
      pages = {103219},
      year = {2021},
      publisher = {Elsevier}
    }
  19. N-ROD: A Neuromorphic Dataset for Synthetic-to-Real Domain Adaptation
    Marco Cannici*, Chiara Plizzari*, Mirco Planamente*, Marco Ciccone, Andrea Bottino, Barbara Caputo, Matteo Matteucci
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), 2021.
    @inproceedings{cannici2021nrod,
      title = {N-ROD: A Neuromorphic Dataset for Synthetic-to-Real Domain Adaptation},
      author = {Cannici*, Marco and Plizzari*, Chiara and Planamente*, Mirco and Ciccone, Marco and Bottino, Andrea and Caputo, Barbara and Matteucci, Matteo},
      booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops)},
      pages = {1342--1347},
      year = {2021}
    }
  20. PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
    Chiara Plizzari*, Mirco Planamente*, Emanuele Alberti, Barbara Caputo
    EPIC Workshop @ CVPR, 2021.
    3rd Place
    @inproceedings{plizzari2021polito,
      title = {PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition},
      author = {Plizzari*, Chiara and Planamente*, Mirco and Alberti, Emanuele and Caputo, Barbara},
      booktitle = {EPIC Workshop @ CVPR},
      year = {2021}
    }

See the full list of publications

Teaching

Course Director and Instructor @ Bocconi University

Teaching Assistant @ Politecnico di Torino

Supervision

As PI of the Vision and Video Understanding group at Bocconi University, I have:

Previously, I co-supervised 4 M.Sc. students and a Ph.D. student at Politecnico di Milano, and 7 M.Sc. theses at Politecnico di Torino.

Research Funding

Honors and Awards

EPIC-Kitchens challenge 2023, 2nd place EPIC-Kitchens challenge 2021, 3rd place

Invited Talks and Seminars

Academic Service

Professional Memberships

Additional Training

ICVSS 2022