Computer vision and machine learning have great potential to endow machines/robots with the (visual) perception of the environment and the intelligence to reason about it, and take decisions. The field has thrived in the past three decades, and it stands now as one of the key technological ingredients for autonomous driving, unmanned drones, and human-robot-collaboration, as well as the pervasive novel asset for other fields of science, including earthquake and weather forecasting.
Our lab is interested in fundamental research and innovation transfer on computer vision and machine learning. Our specific research interests include distributed and multi-agent intelligent systems, perception (detection, recognition, re-identification, forecasting), and general intelligence (reasoning, meta-learning, domain adaptation), within sustainable (low-power-consumption and constrained-computational-resource sensors and devices) and interpretable (interpretable and verifiable AI) frameworks.
RECENT PUBLICATIONS
[All Publications]- Hyp2Nav: Hyperbolic Planning and Curiosity for Crowd NavigationIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
- Contracting Skeletal Kinematics for Human-Related Video Anomaly DetectionPattern Recognition, 2024
- Hyperbolic Active Learning for Semantic Segmentation under Domain ShiftIn International Conference on Machine Learning (ICML), 2024
- PREGO: online mistake detection in PRocedural EGOcentric VideosIn Computer Vision and Pattern Recognition (CVPR), 2024
- About latent roles in forecasting players in team sportsNeural Processing Letters, vol. 56, pp. 1-12, 2024