Rohan C. Choudhury

I’m a 4th-year PhD student in the Robotics Institute at Carnegie Mellon University, advised by Kris Kitani and László Jeni. I’m supported in part by an NSF GRFP Fellowship.

I’m broadly interested in making video understanding faster and more efficient. In particular, I work on enabling vision algorithms to continuously perceive the world in high resolution and at 30+ FPS.

During my graduate studies, I’ve spent time as a research scientist intern at Meta FAIR (with Jing Huang).Before starting my PhD, I was a software engineer at Nuro, where I worked on trajectory forecasting models for self-driving vehicles. Even before that, I graduated from Caltech. When I’m not working on research, I enjoy running, lifting weights, and listening to electronic music.

news

Oct 18, 2024	RLT was accepted to NeurIPS 2024 as a spotlight paper!
Jul 14, 2024	Our paper Video Question Answering with Procedural Programs was accepted to ECCV 2024!

selected papers

NeurIPS

Don’t Look Twice: Faster Video Tranformers with Run-Length Tokenization

Rohan Choudhury, Guanglei Zhu, Sihan Liu, and 3 more authors

NeurIPS, 2024

Awarded Bib Project Page

Spotlight

@article{choudhury2024rlt,
  title = {Don't Look Twice: Faster Video Tranformers with Run-Length Tokenization},
  author = {Choudhury, Rohan and Zhu, Guanglei and Liu, Sihan and Niinuma, Koichiro and Kitani, Kris M. and Jeni, László A.},
  journal = {NeurIPS},
  year = {2024},
  site = {/projects/rlt/}
}

ECCV

Video Question Answering with Procedural Programs

Rohan Choudhury, Koichiro Niinuma, Kris M. Kitani, and 1 more author

ECCV, 2024

arXiv Bib HTML

@article{choudhury2024proviq,
  title = {Video Question Answering with Procedural Programs},
  author = {Choudhury, Rohan and Niinuma, Koichiro and Kitani, Kris M. and Jeni, László A.},
  journal = {ECCV},
  year = {2024},
}

ICRA

JaywalkerVR: A VR System for Collecting Safety-Critical Pedestrian-Vehicle Interactions

Kenta Mukoya, Erica Weng, Rohan Choudhury, and 1 more author

ICRA, 2024

arXiv Bib

@article{mukoya2024jaywalker,
  title = {JaywalkerVR: A VR System for Collecting Safety-Critical Pedestrian-Vehicle Interactions},
  author = {Mukoya, Kenta and Weng, Erica and Choudhury, Rohan and Kitani, Kris M.},
  journal = {ICRA},
  year = {2024},
}

ICCV

TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting

Rohan Choudhury, Kris M. Kitani, and László A. Jeni

ICCV, 2023

arXiv Bib HTML Code

@article{choudhury2023tempo,
  title = {TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting},
  author = {Choudhury, Rohan and Kitani, Kris M. and Jeni, László A.},
  journal = {ICCV},
  year = {2023},
}