Chiara Plizzari
Hello! I’m Chiara and I am a Postdoctoral Researcher at the Smart Eyewear Lab, a joint research center between EssilorLuxottica and Politecnico di Milano. Previously, I was a Student Researcher at Google Research in Zurich, where I had the chance to work in Federico Tombari’s team. I have been a PhD student of the VANDAL (Visual AND Multimodal Applied Learning) laboratory at Politecnico di Torino (Italy), supervised by prof. Barbara Caputo. I was also part of the ELLIS research program co-supervised by Prof. Dima Damen from University of Bristol.
I am interested in video understanding, and intrigued by how vision can be complemented by multiple modalities, including language, audio, and 3D information.
News
| Mar 16, 2025 | Happy to announce that the work I did during my research time at Google has been accepted to CVPR2025!  |
|---|---|
| Apr 16, 2024 | I just started as a Student Researcher in Google Zurich in Federico Tombari’s team! |
| Oct 21, 2023 | I gave a talk on Cross-Domain Egocentric Vision at I-RIM 2023! |
| Oct 3, 2023 | Honored to be part of the organization of the Women in Computer Vision Workshop (WiCV) @ ICCV23! |
| Oct 1, 2023 | Excited to be selected for the Doctoral Consortium @ ICCV23! |
| Jun 29, 2023 | Our work on Mixed Sequence Predictions won the 2nd place at the EPIC-Kitchens Unsupervised Domain Adaptation Challenge at CVPR! 🥈 |
| Feb 1, 2023 | I visited Berkeley Artificial Intelligence Research (BAIR) Lab and started a collaboration with Prof. Angjoo Kanazawa!   |
| Apr 19, 2022 | I gave a talk on Cross-Domain Activity Recognition at University of Bristol to the Machine Learning and Computer Vision group! |
| Mar 29, 2022 | Started a 9-months research visiting @ University of Bristol with Prof. Dima Damen   |
| Jun 29, 2021 | Our work on Relative Norm Alignment won the 3rd place at the EPIC-Kitchens Unsupervised Domain Adaptation Challenge at CVPR! 🥉 |
Selected Publications
-
Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric VideosProceedings of the IEEE/CVF International Conference on Computer Vision, 2025 -
Spatial Cognition from Egocentric Video: Out of Sight, Not Out of MindInternational Conference on 3D Vision, 2025 -
Relative Norm Alignment for Tackling Domain Shift in Deep Multi-modal ClassificationInternational Journal of Computer Vision, 2024 -
What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and LocationsIn Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023 -
An Outlook into the Future of Egocentric VisionIn International Journal of Computer Vision, 2023 -
EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge: Mixed Sequences PredictionIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023 -
E2 (GO) MOTION: Motion Augmented Event Stream for Egocentric Action RecognitionIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022 -
Da4event: towards bridging the sim-to-real gap for event cameras using domain adaptationIEEE Robotics and Automation Letters, 2021 -
Domain generalization through audio-visual relative norm alignment in first person action recognitionIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022 -
Polito-iit submission to the epic-kitchens-100 unsupervised domain adaptation challenge for action recognitionarXiv preprint arXiv:2107.00337, 2021 -
Skeleton-based action recognition via spatial and temporal transformer networksComputer Vision and Image Understanding, 2021