1

HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
Pedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision …
Xihui Liu, Haiyu Zhao, Maoqing Tian, Lu Sheng, Jing Shao, Shuai Yi, Junjie Yan, Xiaogang Wang
PDF Cite Code DOI
Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification
In this paper, we tackle the vehicle Re-identification (ReID) problem which is of great importance in urban surveillance and can be …
Zhongdao Wang, Luming Tang, Xihui Liu, Zhuliang Yao, Shuai Yi, Jing Shao, Junjie Yan, Shengjin Wang, Hongsheng Li, Xiaogang Wang
PDF Cite DOI
Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion
Haiyu Zhao, Maoqing Tian, Shuyang Sun, Jing Shao, Junjie Yan, Shuai Yi, Xiaogang Wang, Xiaoou Tang
PDF Cite Code Dataset DOI
Slicing Convolutional Neural Network for Crowd Video Understanding
Learning and capturing both appearance and dynamic representations are pivotal for crowd video understanding. Convolutional Neural …
Jing Shao, Chen Change Loy, Kai Kang, Xiaogang Wang
Cite DOI
Deeply learned attributes for crowded scene understanding
Crowded scene understanding is a fundamental problem in computer vision. In this study, we develop a multi-task deep model to jointly …
Jing Shao, Kai Kang, Chen Change Loy, Xiaogang Wang
PDF Cite DOI
Scene-Independent Group Profiling in Crowd
Groups are the primary entities that make up a crowd. Understanding group-level dynamics and properties is thus scientifically …
Jing Shao, Chen Change Loy, Xiaogang Wang
PDF Cite DOI