Changxin Gao (高常鑫) cgao@hust.edu.cn

Currently I am an Associate Professor with the School of Automation, Huazhong University of Science and Technology, Wuhan, China. I received the B.S. degree and the Ph.D. degree both from Huazhong University of Science and Technology in 2005 and 2010. My Ph.D. supervisor is Prof. Nong Sang. From 2012 to 2013, I was a postdoctoral researcher in ICTEAM at Université Catholique de Louvain with Prof. Benoit Macq. My research interest includes computer vision, specifically on object detection, object tracking, image and video semantic understanding.

News

2018-12 One paper is accepted to IJCV.

2018-07 One paper is accepted to ECCV2018.

2018-03 One paper is accepted to Pattern Recognition.

2018-02 Two papers are accepted to CVPR2018.

Selected recent publications

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang

ECCV, 2018

[paper] 68.4% Mean IOU, 105FPS on Cityscapes test dataset

Learning a Discriminative Feature Network for Semantic Segmentation

Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao*, Gang Yu, Nong Sang

CVPR, 2018.

[paper]

Learning a Discriminative Prior for Blind Image Deblurring

Lerenhan Li, Jinshan Pan, Wei-Sheng Lai, Changxin Gao, Nong Sang*, Ming-Hsuan Yang

CVPR, 2018.

[paper] [project]

Spatial and Class Structure Regularized Sparse Representation Graph for Semi-Supervised Hyperspectral Image Classification

Yuanjie Shao, Nong Sang*, Changxin Gao, Li Ma

Pattern Recognition, 2018

[paper]

Discriminative Part Selection For Human Action Recognition

Shiwei Zhang, Changxin Gao, Jing Zhang, Feifei Chen, and Nong Sang*

IEEE Transactions on Multimedia, 2018

[paper]

Equidistance Constrained Metric Learning for Person Re-identification

Jin Wang, Zheng Wang, Chao Liang, Changxin Gao*, Nong Sang

Pattern Recognition, 2018

[paper] [code]

Group Sparse Based Mid-level Representation For Action Recognition

Shiwei Zhang, Changxin Gao*, Feifei Chen, Sihui Luo, and Nong Sang

IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017

[paper]

Probabilistic Class Structure Regularized Sparse Representation Graph for Semi-Supervised Hyperspectral Image Classification

Yuanjie Shao, Nong Sang*, Changxin Gao, Li Ma

Pattern Recognition, 2017

[paper]

DeepList: Learning Deep Features with Adaptive Listwise Constraint for Person Re- identification

Jin Wang, Zheng Wang, Changxin Gao*, Nong Sang, Rui Huang

IEEE Transactions on Circuits and Systems for Video Technology, 2017

[paper] [code]

Robust Visual Tracking Using Exemplar-based Detectors

Changxin Gao, Feifei Chen, Jin-Gang Yu, Rui Huang, Nong Sang*

IEEE Transactions on Circuits and Systems for Video Technology, 2017

[paper] [project]

Funds

  • Feature Representation and Metric Learning for Video-based Person Re-identification, NSF of China, 2019.1-2022.12
  • Spatio-temporal Attention based Deep Network for Person Re-identification, NSF of Hubei, 2018.1--2019.12
  • Combining Top-down and Bottom-up Processing for Scene Parsing, NSF of China, 2015.1--2017.12