Peiyun Hu

I am a PhD student (2016-) at the Robotics Institute of Carnegie Mellon University, where I am fortunate to be advised by with Deva Ramanan. Prior to joining CMU, I spent four years at Tsinghua University and two years at UC Irvine.



I am passionate about tackling bottlenecks and challenges of computer vision in the real-world setting.


Active Learning with Partial Feedback
Peiyun Hu, Zack C. Lipton, Anima Anandkumar, Deva Ramanan
International Conference on Learning Representations (ICLR), 2019


Comparing Apples and Oranges: Off-Road Pedestrian Detection on the NREC Agricultural Person-Detection Dataset
Zachary Pezzementi, Trenton Tabor, Peiyun Hu, Jonathan K. Chang, Deva Ramanan, Carl Wellington, Benzun P. Wisely Babu, Herman Herman
Journal of Field Robotics (JFR), 2017
preprint / paper / dataset / video


Finding Tiny Faces
Peiyun Hu, Deva Ramanan
Computer Vision and Pattern Recognition (CVPR), 2017
preprint / paper / project / code / press


Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians
Peiyun Hu, Deva Ramanan
Computer Vision and Pattern Recognition (CVPR), 2016
(Spotlight Presentation)
preprint / paper / project / ext. abstract / slides / talk / poster / code

Professional activities

Served/serving as a reviewer for IJCV, TPAMI, NIPS'19, ICCV'19, ICML'19, CVPR'19, ICLR'19, NIPS'18, CVPR'18

The webpage design was "stolen" from Aayush Bansal, Jon Barron, and Carl Vondrick. Special thanks to them!