Chi Li


Department of Computer Science
Johns Hopkins University
Hackerman 137, 3400 N Charles St.
Baltimore, MD 21218, USA
Email: chi_li [at] jhu [dot] edu

About Me

I obtained the Ph.D. degree from Department of Computer Science, Johns Hopkins University, in Spring 2018. My primary advisor is Prof. Gregory D. Hager. I also collaborate with Austin Reiter, Alan Yuille, Rene Vidal and Nassir Navab. My current research mainly focuses on visual understanding of object properties from semantic class to 3D pose and structure. To solve these problems, I am particularly interested in leveraging scene geometry to enhance deep learning techniques on 2D/3D/Multi-view perception. I also has pratical experience in deploying vision algorithms for various robotic applications like object manipulation and collaborative manufacutring tasks.

I got my B.E. from Cognitive Science Department at Xiamen University in 2012. There I became interested in computer vision while working on dense stereo reconstruction and object tracking with Prof. Hanzi Wang and Dr. Le Lu. I was a research intern on 3D vision for Apple at Summer 2017. I also interned at Media Analytics Group of NEC Laboratories America at Summer 2016, mentored by Zeeshan Zia, Manmohan Chandraker, Quoc-Huy Tran and Xiang Yu. During Summer 2013, I interned with Zicheng Liu, Zhengyou Zhang, and Yinpen Chen at Microsoft Research.


Selected Publications

A Unified Framework for Multi-View Multi-Class Object Pose Estimation

Chi Li, Jin Bai and Gregory D. Hager
European Conference on Computer Vision (ECCV), 2018
PDF Supplementary Material DATA (JHU) More coming soon

Scalable Exemplar-based Subspace Clustering Algorithm for Class-Imbalanced Data

Chong You, Chi Li, Daniel Robinson and Rene Vidal
European Conference on Computer Vision (ECCV), 2018
PDF Code

Deep Supervision with Intermediate Concepts

Chi Li, M. Zeeshan Zia, Quoc-Huy Tran, Xiang Yu, Gregory D. Hager and Manmohan Chandraker
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018
arXiv More coming soon

Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing

Chi Li, M. Zeeshan Zia, Quoc-Huy Tran, Xiang Yu, Gregory D. Hager and Manmohan Chandraker
Computer Vision and Pattern Recognition (CVPR), 2017
PDF Supplementary Material Data(KITTI-3D) Data(CADs) Rendered Images (Chair+Sofa) Rendered Images (Car)

Incremental Scene Understanding on Dense SLAM

Chi Li, Han Xiao, Keisuke Tateno, Federico Tombari, Nassir Navab, Gregory D. Hager
International Conference on Intelligent Robots and Systems (IROS), 2016
Oral Presentation
PDF Video Data

Hierarchical Semantic Parsing for Object Pose Estimation in Densely Cluttered Scenes

Chi Li, Jonathan Bohren, Eric Carlson, Gregory D. Hager.
International Conference on Robotics Automation (ICRA), 2016
PDF Video Project Webpage Data Code

Bridging the Robot Perception Gap With Mid-Level Vision

Chi Li, Jonathan Bohren, Gregory D. Hager.
International Symposium on Robotics Research (ISRR), 2015
Oral Presentation
Revised version in Robotics Research, page 5-20, 2018.
PDF Slides Data Code

Beyond Spatial Pooling: Fine-Grained Representation Learning in Multiple Domains

Chi Li, Austin Reiter, Gregory D. Hager.
Computer Vision and Pattern Recognition (CVPR), 2015
PDF Supplementary Material Project Webpage Data Code

Robust Object Tracking in Crowd Dynamic Scenes Using Explicit Stereo Depth

Chi Li, Le Lu, Gregory D. Hager, Jianyu Tang, Hanzi Wang.
Asian Conference on Computer Vision (ACCV), 2012
PDF Slides Poster Video Supplementary Material


Head of Teaching Assistant, Johns Hopkins University (Fall 2014)
CS 479/679: Representation Learning