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 two years at UC Irvine and four years at Tsinghua University.

Research

I spend most of my time thinking about (1) how can we teach robots to recognize all sorts of objects that these robots might encounter when they go out and operate in an open world? and (2) what is the most efficient way to teach?

teaser_vis

What You See is What You Get: Exploiting Visibility for 3D Object Detection
Peiyun Hu, Jason Ziglar, David Held, Deva Ramanan
arXiv 2019
preprint / video


teaser_seg

Learning to Optimally Segment Point Clouds
Peiyun Hu, David Held*, Deva Ramanan*
IEEE Robotics and Automation Letters (RA-L) and ICRA, 2020
paper / video / code


teaser_alpf

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


teaser_tiny

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


teaser_topdown

Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians
Peiyun Hu, Deva Ramanan
Computer Vision and Pattern Recognition (CVPR), 2016
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