Portal de Periódicos da CAPES

MHSA-Net: Multihead Self-Attention Network for Occluded Person Re-Identification

2022; Institute of Electrical and Electronics Engineers; Volume: 34; Issue: 11 Linguagem: Inglês

10.1109/tnnls.2022.3144163

2162-2388

Hongchen Tan, Xiuping Liu, Baocai Yin, Xin Li,

Human Pose and Action Recognition

This article presents a novel person reidentification model, named multihead self-attention network (MHSA-Net), to prune unimportant information and capture key local information from person images. MHSA-Net contains two main novel components: multihead self-attention branch (MHSAB) and attention competition mechanism (ACM). The MHSAB adaptively captures key local person information and then produces effective diversity embeddings of an image for the person matching. The ACM further helps filter out attention noise and nonkey information. Through extensive ablation studies, we verified that the MHSAB and ACM both contribute to the performance improvement of the MHSA-Net. Our MHSA-Net achieves competitive performance in the standard and occluded person Re-ID tasks.