Pedestrian attribute recognition based on dual self-attention Mechanism

Zhongkui Fan1 and Ye-peng Guan1, 2

  1. School of Communication and Information Engineering, Shanghai University,
    200444 shanghai, China
    {fanzkui, ypguan}
  2. Key Laboratory of Advanced Displays and System Application, Ministry of Education,
    200444 shanghai, China


Recognizing pedestrian attributes has recently obtained increasing attention due to its great potential in person re-identification, recommendation system, and other applications. Existing methods have achieved good results, but these methods do not fully utilize region information and the correlation between attributes. This paper aims at proposing a robust pedestrian attribute recognition framework. Specifically, we first propose an end-to-end framework for attribute recognition. Secondly, spatial and semantic self-attention mechanism is used for key points localization and bounding boxes generation. Finally, a hierarchical recognition strategy is proposed, the whole region is used for the global attribute recognition, and the relevant regions are used for the local attribute recognition. Experimental results on two pedestrian attribute datasets PETA and RAP show that the mean recognition accuracy reaches 84.63% and 82.70%. The heatmap analysis shows that our method can effectively improve the spatial and the semantic correlation between attributes. Compared with existing methods, it can achieve better recognition effect.

Key words

pedestrian attribute recognition; spatial self-attention; semantic self-attention; deep learning

Digital Object Identifier (DOI)

Publication information

Volume 20, Issue 2 (April 2023)
Special Issue on Machine Learning-based Decision Support Systems in IoT systems
Year of Publication: 2023
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Fan, Z., Guan, Y.: Pedestrian attribute recognition based on dual self-attention Mechanism. Computer Science and Information Systems, Vol. 20, No. 2, 793–812. (2023),