top of page

From Perception to Agency: The Cognitive Stack for Video Task Assistants 

From Pixels to Coaches: AI That Sees, Understands and Teaches 

Paradoxes of Language-Driven Video Understanding 

Video AI Symposium (September 2025)

BIMBA: Selective-Scan Compression for Long-Range Video Question-Answering 

Understanding Complex Human Activities in Long Videos 

Is Space-Time Attention All You Need For Video Understanding?

Video Understanding with Modern Language Models

Contact

Prospective Graduate Students: I am recruiting motivated students in computer vision. Please email me a list of your prior publications and your CV.

Undergraduates at UNC: If you are interested in computer vision, especially its applications to sports, email me your CV and transcript with your GPA.

©2024 by Gedas Bertasius

bottom of page