Associate Professor @ CIMeC/DISI - University of Trento
Palazzo Fedrigotti - Room 216 - Rovereto
Polo Ferrari - Room 110 - Povo 2
I am Paolo Rota, associate professor at the University of Trento, working in computer vision, machine learning, and multimodal AI. My research focuses on vision-language models and activity recognition, with applications in video analytics and industrial AI.
Recently, I have been exploring topics such as zero-shot action recognition, temporal action localization, and vocabulary-free image classification, contributing to publications at conferences like CVPR, NeurIPS, and ICCV. I enjoy tackling challenges in open-world recognition and multimodal learning, always looking for ways to improve AI’s practical impact.
Outside of academia, I co-founded Mountain Maps, a startup that uses AI to enhance outdoor navigation and help people explore mountain environments more safely and enjoyably.
Shiyao’s paper has been accepted to 3DV 2026!
The work focuses on Motion Captioning, with the goal of developing a model that can describe not only what action is happening, but also when it occurs by accurately identifying its temporal boundaries, as the title: Dense Motion Captioning.
For more details, visit the project webpage: https://xusy2333.com/demo/
Benedetta's work serves as a benchmark to evaluate how models handle video similarity based on various concepts. Tom's work instead reexamines the feature reliance of our nice old CNNs, analysing the results on controlled suppressions.
Ale successfully defended his PhD "cum laude"! Congrats!!!
The paper is entitled "Automatic benchmarking of Large Multimodal Models via iterative experiment programming" and you can find it here. The idea is to benchmark LMMs using an LLM orchestrator that controls tools (e.g., datasets and benchmarks).
