Abstract: Video understanding is one of the fundamental problems in computer vision with various applications, including autonomous vehicles, robot learning, and visual perception. Although we have witnessed multiple works in video understanding in the last few years, there are many more challenging video understanding problems that are still unsolved. In this talk, I will present some of our recent work in video understanding, including cross-modal self-supervised learning of video and audio representations and open-world instance segmentation. Finally, I will speculate on several potential future research directions in this area.