Seminar

CVL Talk: From Video to Unsupervised Semantic 4D Reconstruction - James Tompkin, Browns

Abstract:

Pose estimation and tracking are among the fundamental problems in computer vision and crucial tasks in many vision applications ranging from sports to human-computer interaction to the study of collective behaviour. Within our centre for the Advanced Study of Collective Behaviour, among other things, we study the collective behaviour of animals. That is why we are interested in real-time multi-animal pose estimation and tracking in the wild. The problem in achieving this goal is that the availability of annotated tracking data for animals is limited, especially for multiple objects. In this talk I would like to show you how we try to bridge this gap between the lack of annotated animal data and the need for real-time multi-animal pose estimation and tracking for the study of collective behaviour.

Bio:

James Tompkin is the John E. Savage Assistant Professor of Computer Science at Brown University. His research at the intersection of computer vision, computer graphics, and human-computer interaction helps develop new visual computing tools and experiences. His doctoral work at University College London on large-scale video processing and exploration techniques led to creative exhibition work in the Museum of the Moving Image in New York City. Postdoctoral work at Max-Planck-Institute for Informatics and Harvard University helped create new methods to edit content within images and videos. Recent research has developed new techniques for low-level depth reconstruction, view synthesis for VR, and content editing and generation.

Zoom Link

You can see the other CVPR 2023 UBC events here.