S
Song-Hai Zhang
Researcher at Tsinghua University
Publications - 76
Citations - 2142
Song-Hai Zhang is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 17, co-authored 66 publications receiving 1148 citations.
Papers
More filters
Proceedings ArticleDOI
Traffic-Sign Detection and Classification in the Wild
TL;DR: A large traffic-sign benchmark from 100000 Tencent Street View panoramas is created, going beyond previous benchmarks, and it is demonstrated how a robust end-to-end convolutional neural network (CNN) can simultaneously detect and classify trafficsigns.
Posted Content
Attention Mechanisms in Computer Vision: A Survey.
Meng-Hao Guo,Tian-Xing Xu,Jiangjiang Liu,Zheng-Ning Liu,Peng-Tao Jiang,Tai-Jiang Mu,Song-Hai Zhang,Ralph R. Martin,Ming-Ming Cheng,Shi-Min Hu +9 more
TL;DR: A comprehensive review of attention mechanisms in computer vision can be found in this article, which categorizes them according to approach, such as channel attention, spatial attention, temporal attention and branch attention.
Proceedings ArticleDOI
Pose2Seg: Detection Free Human Instance Segmentation
Song-Hai Zhang,Ruilong Li,Xin Dong,Paul L. Rosin,Zixi Cai,Xi Han,Dingcheng Yang,Haozhi Huang,Shi-Min Hu +8 more
TL;DR: This paper introduces a new benchmark "Occluded Human (OCHuman)", which focuses on occluded humans with comprehensive annotations including bounding-box, human pose and instance masks, and demonstrates that this pose-based framework can achieve better accuracy than the state-of-art detection-based approach on the human instance segmentation problem, and can moreover better handle occlusion.
Journal ArticleDOI
Vectorizing Cartoon Animations
TL;DR: The new trapped-ball segmentation method is presented, which is fast, supports nonuniformly colored regions, and allows robust region segmentation even in the presence of imperfectly linked region edges.
Proceedings ArticleDOI
Example-Guided Style-Consistent Image Synthesis From Semantic Labeling
TL;DR: The authors propose a style consistency discriminator to determine whether a pair of images are consistent in style, and an adaptive semantic consistency loss for synthesizing style-consistent results to the exemplar.