The Computer Vision Center (CVC) coordinates the model transfer and deployment through use cases. The CVC leads the Document Understanding use case, developing systems to automatically fill forms with knowledge extracted from large unstructured document collections. In the use case of autonomous driving, on the one hand, CVC will use multimodal foundational models to leverage prior knowledge during the training of sensorimotor deep models (aka end-to-end driving models); on the other hand, CVC wil use multimodal foundational models for automatic real-to-sim scenario scripting (in CARLA simulator), i.e., to speed up the scripting of simulated scenarios by leveraging relevant traffic events recorded from real vehicles.
The Computer Vision Center (CVC) at Universitat Autònoma de Barcelona is a leading research institute in computer vision. As a non-profit, it drives cutting-edge research, technology transfer, and expert training. Its work spans AI, image analysis, and neuroscience, contributing to ethical AI through projects like Horizon Europe. CVC fosters collaboration via events and education, shaping the future of visual technologies with a strong commitment to equality and sustainability.
Country
Spain
Role in the project
Use Cases on Autonomous Driving, and Document Understanding.
Website