filmov
tv
DINOv2 Revisited
Показать описание
In this video, dr. Pablo G. Morato, a postdoc researcher from AiDAPT lab at Delft University of Technology, explains the seminal paper from the Meta research group, called "DINOv2: Learning Robust Visual Features without Supervision". The paper introduces a vision foundation model that can transform images and videos into abstract but powerful representations. If you are curious join us in this coffee talk.