user_image

Perception and Intelligence Laboratory (PINlab)

Department of Computer Science

Sapienza University of Rome, Italy

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]
  1. Alessandro Flaborea,  Guido Maria D’Amely Di Melendugno,  Leonardo Plini,  Luca Scofano,  Edoardo De Matteis,  Antonino Furnari,  Giovanni Maria Farinella,  and Fabio Galasso
    PREGO: online mistake detection in PRocedural EGOcentric Videos
    In Computer Vision and Pattern Recognition (CVPR), 2024
  2. Luca Scofano,  Alessio Sampieri,  Giuseppe Re,  Matteo Almanza,  Alessandro Panconesi,  and Fabio Galasso
    About latent roles in forecasting players in team sports
    Neural Processing Letters, vol. 56, pp. 1-12, 2024
  3. Luca Franco,  Paolo Mandica,  Konstantinos Kallidromitis,  Devin Guillory,  Yu-Teng Li,  and Fabio Galasso
    Hyperbolic Active Learning for Semantic Segmentation under Domain Shift
    In International Conference on Machine Learning (ICML), 2024
  4. Luca Scofano,  Alessio Sampieri,  Elisabeth Schiele,  Edoardo De Matteis,  Laura Leal-Taixé,  and Fabio Galasso
    Staged Contact-Aware Global Human Motion Forecasting
    In British Machine Vision Conference (BMVC), 2023
  5. Alessandro Flaborea,  Luca Collorone,  Guido Maria D’Amely Di Melendugno,  Stefano D’Arrigo,  Bardh Prenkaj,  and Fabio Galasso
    Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 10318-10329, 2023