top of page
UNC_Zoom_Backgrounds_C.jpg
gb.jpg

Gedas Bertasius

Assistant Professor

I am an Assistant Professor in the Computer Science department at the University of North Carolina, Chapel Hill. My research interests are in computer vision and machine learning. In particular, I'm interested in video understanding, human behavior modeling, and multi-modal deep learning. I'm also passionate about using computer vision for advanced basketball analytics. 

Research Overview

Virtual AI Assistants

Designing AI systems that can help people with various daily tasks.

Developing computer vision tools for advanced basketball analytics.

Multimodal Learning

Computer Vision for Basketball

Building models that learn from video, audio, and text.

Video Modeling

Developing spatiotemporal models for automatic video analysis.

 News

Contact

Selected Projects

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

[arxiv] [code] [bibtex

Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos

Md Mohaiminul Islam, Tushar Nagarajan, Huiyu Wang, Fu-Jen Chu, Kris Kitani, Gedas Bertasius, Xitong Yang

ECCV 2024 (Oral)

[arxiv] [project page[bibtex

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

[arxiv] [project website] [blog] [video] [bibtex

Video ReCap: Recursive Captioning of Hour-Long Videos

Md Mohaiminul Islam, Ngan Ho, Xitong Yang, Tushar Nagarajan, Lorenzo Torresani, Gedas Bertasius

CVPR 2024

[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

[arxiv] [code] [bibtex

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

Gedas Bertasius, Heng Wang, Lorenzo Torresani

ICML 2021

[arxiv] [code] [talk] [slides] [blog] [VentureBeat] [SiliconAngle] [bibtex]

bottom of page