Content

Speaker

Boqing Gong

Abstract

This talk explores the challenges of out-of-domain (OOD) generalization in computer vision, encompassing tasks like domain adaptation, webly supervised learning, and long-tailed recognition. I will review some principles and techniques underlying the seemingly diverse tasks and then connect them to the recent development of generalist vision systems, showcasing VideoPrism–a state-of-the-art generalist video encoding–and ongoing research into image and video generation models.

Bio

Boqing Gong is a computer science faculty member at Boston University and a part-time research scientist at Google DeepMind. His research focuses on AI models' generalization and efficiency and the visual analytics of objects, scenes, human activities, and their interactions.