Paolo Rota

Tenure-track Assistant Professor (RTDb), CIMeC/DISI - University of Trento
Co-Founder, Mountain Maps s.r.l.

Hi, I’m Paolo, a tenure-track assistant professor at the Center for Mind and Brain (CIMeC) and the Department of Information Engineering and Computer Science (DISI) of the University of Trento.

I obtained my Ph.D. from the University of Trento in 2015, specializing in Computer Vision perspective of Social Interaction Analysis.

After completing his Ph.D., Paolo pursued a Postdoctoral position at TU Wien from 2015 to 2017. Following that, I held another Postdoctoral position at the IIT of Genova in 2017-2018. Subsequently, I continued my academic journey as a Postdoc at the Industrial Engineering Department of the University of Trento in 2018-2019 and as RTDa at the Department of Information Engineering and Computer Science until 2022.

My research interests primarily revolve around topics related to Computer Vision, with a recent focus on Natural Language Supervision for Video Scene Understanding. I am member of the ELLIS society and CVPL.

I also co-founded Mountain Maps, an AI-powered navigator meant for mountain enthusiasts.



Resources for my teaching activities.
  • Grounded Language Processing - LM Artificial Intelligence Systems - Fall 2023
  • Introduction to Machine learning - LM Data Science - Spring 2023
  • Introduction to Python - LM Cognitive Science - Fall 2022
  • Recent Publications

    Please refer to my google scholar profile for more information.
    Vocabulary-free Image Classification, 2023, NeurIPS
    Conti, A. , Fini, E. , Mancini, M. , Rota, P. , Wang, Y. , Ricci, E.
    The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation, 2023, ICCV
    Zara, G. , Conti, A. , Roy, S. , Lathuilière, S. , Rota, P. , Ricci, E.
    AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation, 2023, CVPR
    Zara, G. , Roy, S. , Rota, P. , Ricci, E.
    Rotation Synchronization via Deep Matrix Factorization, 2023, ICRA
    Tejus, G. , Zara, G. , Rota, P. , Fusiello, A. , Ricci, E. , Arrigoni, F.
    Deep Unsupervised Key Frame Extraction for Efficient Video Classification, 2022, ACM Transactions on Multimedia Computing, Communications and Applications
    Tang, H. , Ding, L. , Wu, S. , Ren, B. , Sebe, N. , Rota, P.
    Unsupervised Domain Adaptation for Video Transformers in Action Recognition, 2022, ICPR
    Turrisi Da Costa, V , Zara, G , Rota, P. , Olivera-dos Santos, T. , Sebe, N. , Murino, V. , Ricci, E.
    Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition, 2022, BMVC 2022
    Conti, A. , Rota, P. , Wang, Y. , Ricci, E.
    Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation, 2022, T-PAMI
    Yang, G. , Fini, E. , Xu, D. , Rota, P. , Ding, M. , Nabi, M. , Almaeda-Pineda, X. , Ricci, E.
    Low-budget label query through domain alignment enforcement, 2022, CVIU
    Saltori, C. , Rota, P. , Sebe, N. , Almeida, J.
    Continual Attentive Fusion for Incremental Learning in Semantic Segmentation, 2022, Transaction on MultiMedia
    Yang, G. , Fini, E. , Xu, D. , Rota, P. , Ding, M. , Tang, H. , Almaeda-Pineda, X. , Ricci, E.
    Curriculum Learning: A Survey, 2022, IJCV
    Soviany, P. , Ionescu, R. , Rota, P. , Sebe, N.