Overview
The large quantity of data available on the internet has led to the deployment of extremely powerful artificially intelligent models. Such models, however, require an important amount of computational resources for training and inference. This limits the deployment of such models in a real-world scenario outside the sandbox of massive data centers.
Inspired by the capability of human brains to learn new concepts efficiently, the main activity of the group is to research novel training techniques that reduce the computational burden of neural models, improving the ability to learn new concepts continuously and extract knowledge from different modalities.
Our research group specializes in the comprehensive study of Computer Vision and Pattern Recognition. We have a specific focus on exploring the intersection of text and images through Multimodality. One of our primary objectives in the near future is to leverage diverse modalities to expand the boundaries of closed-set classification in both images and videos.
Research directions
The key topics of interest are:
- Video Understanding
- Action and activity recognition
- Domain Adaptation
- Self-supervised learning
- Natural Language Supervision
- Open-vocabulary recognition
Members
- Paolo Rota, Principal Investigator
- Giacomo Zara (co-supervised with prof. Elisa Ricci)
- Alessandro Conti (co-supervised with prof. Elisa Ricci)
- Benedetta Liberatori (co-supervised with prof. Elisa Ricci)
Publications
For a complete list see Paolo Rota scholar profile.