Back to Search Start Over

ASTA-Net: Adaptive Spatio-Temporal Attention Network for Person Re-Identification in Videos

Authors :
Meng Wang
Zheng-Jun Zha
Haoze Wu
Xierong Zhu
Jiawei Liu
Source :
ACM Multimedia
Publication Year :
2020
Publisher :
ACM, 2020.

Abstract

The attention mechanism has been widely applied to enhance pedestrian representation for person re-identification in videos. However, most existing methods learn the spatial and temporal attention separately, and thus ignore the correlation between them. In this work, we propose a novel Adaptive Spatio-Temporal Attention Network (ASTA-Net) to adaptively aggregate the spatial and temporal attention features into discriminative pedestrian representation for person re-identification in videos. Specifically, multiple Adaptive Spatio-Temporal Fusion modules within ASTA-Net are designed for exploring precise spatio-temporal attention on multi-level feature maps. They first obtain the preliminary spatial and temporal attention features via the spatial semantic relations for each frame and temporal dependencies among inconsecutive frames, then adaptively aggregate the preliminary attention features on the basis of their correlation. Moreover, an Adjacent-Frame Motion module is designed to explicitly extract motion patterns according to the feature-level variation among adjacent frames. Extensive experiments on the three widely-used datasets, i.e., MARS, iLIDS-VID and PRID2011, have demonstrated the effectiveness of the proposed approach.

Details

Database :
OpenAIRE
Journal :
Proceedings of the 28th ACM International Conference on Multimedia
Accession number :
edsair.doi...........e8b184fb4284b4f71ea234284b0850c7
Full Text :
https://doi.org/10.1145/3394171.3413843