Gedas Bertasius
Assistant Professor
I am an Assistant Professor in the Computer Science department at the University of North Carolina, Chapel Hill. Before joining UNC, I was a postdoctoral researcher at Facebook AI Research (FAIR) working with Lorenzo Torresani. I finished my Ph.D. at the University of Pennsylvania, advised by Jianbo Shi, and my undergraduate degree at Dartmouth College.
Research
I lead the Multimodal Video Perception (MVP) group at UNC. We develop foundational models for multimodal video understanding, enabling machines to comprehend, reason about, and interact with complex video, audio, and language data. Moving beyond perception, we ask: what spatiotemporal abstractions are needed for AI to truly grasp complex human behaviors over long horizons? Representative projects include TimeSformer, Video ReCap, LLoVi, BIMBA, VideoTree.
Video Recognition
Developing spatiotemporal models for automatic video analysis (e.g., TimeSformer, ViS4mer).
Multimodal AI
Building models that can learn from video, audio, and text (e.g., Video ReCap, LLoVi, BIMBA).
Perceptual Agents
Sports Analytics
Elevating strategic insights using state-of-the-art multimodal video models (e.g., BASKET).
Generative Video Modeling
Selected Projects
BIMBA: Selective-Scan Compression for Long-Range Video Question Answering
Md Mohaiminul Islam, Tushar Nagarajan, Huiyu Wang, Gedas Bertasius, Lorenzo Torresani
CVPR 2025 (1st Place Winner at CVPR 2025 Ego4D EgoSchema Challenge)
[arxiv] [project page] [code] [model] [demo] [bibtex]
BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation
Yulu Pan, Ce Zhang, Gedas Bertasius
CVPR 2025
[arxiv] [project page] [code] [data] [bibtex]
A Simple LLM Framework for Long-Range Video Question-Answering
Ce Zhang, Taixi Lu, Md Mohaiminul Islam, Ziyang Wang, Shoubin Yu, Mohit Bansal, Gedas Bertasius
EMNLP 2024
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Kristen Grauman, Andrew Westbury, Lorenzo Torresani, Kris Kitani, Jitendra Malik, Gedas Bertasius, ... , Michael Wray
CVPR 2024
Video ReCap: Recursive Captioning of Hour-Long Videos
Md Mohaiminul Islam, Ngan Ho, Xitong Yang, Tushar Nagarajan, Lorenzo Torresani, Gedas Bertasius
CVPR 2024 (Egocentric Vision Distinguished Paper Award)
[arxiv] [project website] [code] [dataset] [bibtex]
VindLU: A Recipe for Effective Video-and-Language Pretraining
Feng Cheng, Xizi Wang, Jie Lei, David Crandall, Mohit Bansal, Gedas Bertasius
CVPR 2023
Is Space-Time Attention All You Need for Video Understanding?
Gedas Bertasius, Heng Wang, Lorenzo Torresani
ICML 2021 (Top-5 Most Impactful ICML 2021 Paper)
[arxiv] [code] [talk] [slides] [blog] [VentureBeat] [SiliconAngle] [bibtex]