Luca Zanella

University of Trento

profile_pic.png

PhD Student,

University of Trento

Trento, Italy

Hi! I’m Luca, a PhD student in the Multimedia and Human Understanding Group at the University of Trento, Italy, supervised by Prof. Elisa Ricci and co-advised by Dr. Massimiliano Mancini.

Before my doctoral studies, I was a research assistant at Fondazione Bruno Kessler, leading the development of video understanding technologies in the European projects MARVEL and PROTECTOR.

My research focuses on vision-language models for understanding videos from diverse domains, including step grounding in instructional videos, video-language alignment using real and synthetic videos, and anomaly detection in surveillance footage.

Contact: luca [dot] zanella-3 [at] unitn [dot] it

news

Feb 26, 2025 Our paper “Can Text-to-Video Generation help Video-Language Alignment?” is accepted to CVPR 2025! Also honored to be among the outstanding reviewers.
Sep 04, 2024 Our paper “Delving into clip latent space for video anomaly recognition” is accepted to CVIU!
Feb 27, 2024 Our paper “Harnessing large language models for training-free video anomaly detection” is accepted to CVPR 2024!

selected publications

  1. zanella2025can.png
    Can Text-to-Video Generation help Video-Language Alignment?
    Luca Zanella, Massimiliano Mancini, Willi Menapace , and 3 more authors
    In Proceedings of the Computer Vision and Pattern Recognition Conference , 2025
  2. zanella2024harnessing.png
    Harnessing Large Language Models for Training-free Video Anomaly Detection
    Luca Zanella, Willi Menapace, Massimiliano Mancini , and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2024
  3. zanella2023delving.png
    Delving into clip latent space for video anomaly recognition
    Luca Zanella, Benedetta Liberatori, Willi Menapace , and 3 more authors
    Computer Vision and Image Understanding, 2024
  4. mattolin2023confmix.png
    Confmix: Unsupervised domain adaptation for object detection via confidence-based mixing
    Giulio Mattolin, Luca Zanella, Elisa Ricci , and 1 more author
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision , 2023