Peng Lei
Address: 1148 Kelley Engineering Center
School of Electrical Engineering and Computer Science
Oregon State University
Corvallis, OR 97331
Email: leip at oregonstate dot edu
Web: http://web.engr.oregonstate.edu/~leip/


I am a Ph.D. candidate in the School of Electrical Engineering and Computer Science at the Oregon State University. My academic advisor is Prof. Sinisa Todorovic. My research interests include action segmentation, semantic video segmentation and motion estimation, mainly focusing on using deep learning methods for solving these problems. Before I joined OSU, I got my B.E. degree in Software Engineering from the Hubei University of Technology, Wuhan, China and my M.S. degree in Computer Science from the Beijing Institute of Technology, Beijing, China. You can download my full CV.

News


Publications


Temporal Deformable Residual Networks for Action Segmentation in Videos
Peng Lei and Sinisa Todorovic
Computer Vision and Pattern Recognition (CVPR), Salt Lake City, 2018
[Paper]

 

Boundary Flow: A Siamese Network that Predicts Boundary Motion without Training on Motion
Peng Lei, Fuxin Li and Sinisa Todorovic
Computer Vision and Pattern Recognition (CVPR), Salt Lake City, 2018
[Paper]

 

Multiple-Instance Video Segmentation with Sequence-Specific Object Proposals
A. Shaban, A. Firl, A. Humayun, J. Yuan, X. Wang, P. Lei, N. Dhanda, B. Boots, J. M. Rehg, F. Li
The 2017 DAVIS Challenge on Video Object Segmentation - CVPR 2017 Workshops
[Paper]

 

Recurrent Temporal Deep Field for Semantic Video Labeling
Peng Lei and Sinisa Todorovic
European Conference on Computer Vision (ECCV), Amsterdam, 2016
[Paper][Supp][Poster]

 

Modeling Human-Skeleton Motion Patterns Using Conditional Deep Boltzmann Machine
Peng Lei and Sinisa Todorovic
International Conference on Pattern Recognition (ICPR), Cancun, Mexico, 2016
[Paper][Videos][Poster]

 

HiRF: Hierarchical Random Field for Collective Activity Recognition in Videos
Mohamed R. Amer, Peng Lei and Sinisa Todorovic
European Conference on Computer Vision (ECCV), Zurich, 2014
[Paper]

 

Robust Tracking by Accounting for Hard Negatives Explicitly
Peng Lei, Tianfu Wu, Mingtao Pei, Anlong Ming and Zhenyu Yao
International Conference on Pattern Recognition (ICPR), Tsukuba Science City, Japan, 2012
[Paper]

 

Courses


Links