Correlation Graph Convolutional Network for Pedestrian Attribute Recognition

The pedestrian attribute recognition aims at generating the structured description of pedestrian, which plays an important role in surveillance. However, it is difficult to achieve accurate recognition results due to diverse illumination, partial body occlusion and limited resolutions. Therefore, th...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia 2022-01, Vol.24, p.49-60
Main Authors: Fan, Haonan, Hu, Hai-Miao, Liu, Shuailing, Lu, Weiqing, Pu, Shiliang
Format: Article
Language:English
Subjects:
Artificial neural networks
Comprehensive relationship Framework
Correlation
Correlation Graph Convolutional Network
Hair
Hierarchical Relation
Image resolution
Inter Relation
Lighting
Manifolds
Mathematical analysis
Multilayers
Occlusion
Pedestrian Attribute Recognition
Recognition
Spatial Relation
Surveillance
Task analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The pedestrian attribute recognition aims at generating the structured description of pedestrian, which plays an important role in surveillance. However, it is difficult to achieve accurate recognition results due to diverse illumination, partial body occlusion and limited resolutions. Therefore, this paper proposes a comprehensive relationship framework for comprehensively describing and utilizing relations among attributes, describing different type of relations in the same dimension, and implementing complex transfers of relations in a GCN manner. This framework is named Correlation Graph Convolutional Network (CGCN). Based on the proposed framework, the feature vectors are built to associate attributes with image features and generate different relation matrices through self-attention among different feature vectors, describing different attribute relations. Then, we conduct multi-layer transfer of attribute relations by means of graph convolution, realizing complex utilization of attribute relations. In addition, the relations among attributes are fully exploited and two types of relations, namely the explicit and implicit relations, are proposed to be integrate into the proposed comprehensive relationship framework. The experimental results on RAP and PETA demonstrate that the recognition performance of the proposed CGCN can obviously outperform the state-of-the-arts, and moreover, the CGCN can achieve a better synergy with different relations.
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2020.3045286