Geodesic
Pedestrian attribute recognition based on dual self-attention Mechanism
Computer Science and Information Systems, Tome 20 (2023) no. 2.

Voir la notice de l'article provenant de la source Computer Science and Information Systems website

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.
Keywords: pedestrian attribute recognition; spatial self-attention; semantic self-attention; deep learning 
@article{CSIS_2023_20_2_a12,
     author = {Zhongkui Fan and Ye-peng Guan},
     title = {Pedestrian attribute recognition based on dual self-attention {Mechanism}},
     journal = {Computer Science and Information Systems},
     publisher = {mathdoc},
     volume = {20},
     number = {2},
     year = {2023},
     url = {http://geodesic.mathdoc.fr/item/CSIS_2023_20_2_a12/}
}
TY  - JOUR
AU  - Zhongkui Fan
AU  - Ye-peng Guan
TI  - Pedestrian attribute recognition based on dual self-attention Mechanism
JO  - Computer Science and Information Systems
PY  - 2023
VL  - 20
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/CSIS_2023_20_2_a12/
ID  - CSIS_2023_20_2_a12
ER  - 
%0 Journal Article
%A Zhongkui Fan
%A Ye-peng Guan
%T Pedestrian attribute recognition based on dual self-attention Mechanism
%J Computer Science and Information Systems
%D 2023
%V 20
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/CSIS_2023_20_2_a12/
%F CSIS_2023_20_2_a12
Zhongkui Fan; Ye-peng Guan. Pedestrian attribute recognition based on dual self-attention Mechanism. Computer Science and Information Systems, Tome 20 (2023) no. 2. http://geodesic.mathdoc.fr/item/CSIS_2023_20_2_a12/