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 -
An Outlook into the Future of Egocentric VisionIn International Journal of Computer Vision, 2023 -
LCMV: Lightweight Classification Module for Video Domain AdaptationIn International Conference on Image Analysis and Processing, 2023 -
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 -
EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge: Mixed Sequences PredictionIn Proceedings of the IEEE/CVF International Conference on Computer Vision Workshop, 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 -
Test-Time Adaptation for Egocentric Action RecognitionIn International Conference on Image Analysis and Processing, 2022 -
Da4event: towards bridging the sim-to-real gap for event cameras using domain adaptationIEEE Robotics and Automation Letters, 2021 -
N-rod: A neuromorphic dataset for synthetic-to-real domain adaptationIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 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