Alessandro Conti
PhD student @ University of Trento.
Computer vision hacker, unorganized thinker.
Education
Nov 2021 - Today
PhD in Artificial Intelligence, University of Trento
Sep 2019 - Oct 2021
MSc in Computer Science, University of Trento
Experience
Jun 2024 - Sep 2024
Research Intern, Apple
Feb 2023 - Feb 2024
Teaching Assistant, University of Trento
Nov 2021 - Sep 2024
Junior Researcher for SPRING, University of Trento
Mar 2021 - Sep 2021
Research Intern, Fondazione Bruno Kessler
Alessandro Conti is a PhD student at the University of Trento, Italy. He is member of the Multimedia Human Understanding Group (MHUG). His research interests include computer vision, multimodal learning, and self-supervised learning.
Papers
On Large Multimodal Models as Open-World Image Classifiers
A. Conti, M. Mancini, E. Fini, Y. Wang, P. Rota, E. Ricci
arXiv preprint, 2025
Compositional Caching for Training-free Open-vocabulary Attribute Detection
M. Garosi, A. Conti, G. Liu, E. Ricci, M. Mancini
Computer Vision and Pattern Recognition (CVPR), 2025
Exploring fine-grained retail product discrimination with zero-shot object classification using vision-language models
A. O. Tur, A. Conti, C. Beyan, D. Bosscaini, R. Larcher, S. Messelodi, F. Poiesi, E. Ricci
Research and Technologies for Society and Industry Innovation (RTSI), 2024
Automatic benchmarking of large multimodal models via iterative experiment programming
A. Conti, E. Fini, P. Rota, Y. Wang, M. Mancini, E. Ricci
arXiv preprint, 2024
Vocabulary-free Image Classification and Semantic Segmentation
A. Conti, E. Fini, M. Mancini, P. Rota, Y. Wang, E. Ricci
arXiv preprint, 2024
Socially Pertinent Robots in Gerontological Healthcare
X. Alameda-Pineda, A. Addlesee, D. Hernandez Garcia, C. Reinke, S. Arias, F. Arrigoni, A. Auternaud, L. Blavette, C. Beyan, L. Gomez Cámara, O. Cohen, A. Conti, C. Dondrup, Y. Ellinson, F. Ferro, S. Gannot, F. Gras, N. Gunson, R. Horaud, M. D’Incà, I. Kimouche, S. Lemaignan, O. Lemon, C. Liotard, R. Madhavan, L. Marchionni, M. Moradi, T. Pajdla, M. Pino, M. Polic, M. Py, A. Rado, B. Ren, E. Ricci, A. Rigaud, P. Rota, M. Romeo, N. Sebe, W. Sieinska, P. Tandeitnik, F. Tonini, N. Turro, T. Wintz, Y. Yu
arXiv preprint, 2024
Test-time zero-shot temporal action localization
B. Liberatori, A. Conti, P. Rota, Y. Wang, E. Ricci
Computer Vision and Pattern Recognition (CVPR), 2024
Vocabulary-free Image Classification
A. Conti, E. Fini, M. Mancini, P. Rota, Y. Wang, E. Ricci
Neural Information Processing Systems (NeurIPS), 2023
The unreasonable effectiveness of Large Language-Vision Models for source-free video domain adaptation
G. Zara*, A. Conti*, S. Roy, S. Lathuilière, P. Rota, E. Ricci
International Conference on Computer Vision (ICCV), 2023
Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition
A. Conti, P. Rota, Y. Wang, E. Ricci
British Machine Vision Conference (BMVC), 2022
Multimodal emotion recognition with modality-pairwise unsupervised contrastive loss
R. Franceschini, E. Fini, C. Beyan, A. Conti, F. Arrigoni, E. Ricci
International Conference on Pattern Recognition (ICPR), 2022
Projects
SPRING - Socially Pertinent Robots in Gerontological Healthcare
EU H2020-ICT Research and Innovation Action