Visual-Semantic Graph Reasoning for Pedestrian Attribute Recognition
Li QZ(李乔哲); Zhao X(赵鑫); He R(赫然); Huang KQ(黄凯奇)
Conference NameThirty-Third AAAI Conference on Artificial Intelligence (AAAI-19)
Conference Date2019-1-27
Conference Place夏威夷,美国

Pedestrian attribute recognition in surveillance is a challenging task due to poor image quality, significant appearance variations and diverse spatial distribution of different attributes. This paper treats pedestrian attribute recognition as a sequential attribute prediction problem and proposes a novel visual-semantic graph reasoning framework to address this problem. Our framework contains a spatial graph and a directed semantic graph. By performing reasoning using the Graph Convolutional Network (GCN), one graph captures spatial relations between regions and the other learns potential semantic relations between attributes. An end-to-end architecture is presented to perform mutual embedding between these two graphs to guide the relational learning for each other. We verify the proposed framework on three large scale pedestrian attribute datasets including PETA, RAP, and PA100k. Experiments show superiority of the proposed method over state-of-the-art methods and effectiveness of our joint GCN structures for sequential attribute prediction.

Indexed ByEI
Document Type会议论文
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Li QZ,Zhao X,He R,et al. Visual-Semantic Graph Reasoning for Pedestrian Attribute Recognition[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
4884-Article Text-79(403KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li QZ(李乔哲)]'s Articles
[Zhao X(赵鑫)]'s Articles
[He R(赫然)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li QZ(李乔哲)]'s Articles
[Zhao X(赵鑫)]'s Articles
[He R(赫然)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li QZ(李乔哲)]'s Articles
[Zhao X(赵鑫)]'s Articles
[He R(赫然)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 4884-Article Text-7950-1-10-20190709 (3).pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.