Share Email Print

Proceedings Paper • new

A plug-and-play LSTM-based attention module for person re-identification
Author(s): Zhengxin Zeng; Zhuqing Jiang; Aidong Men; Guodong Ju
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Spatial attention mechanism is widely used to extract local feature in person re-identification. However, some existing multi-stage spatial attention structures lack flexibility and require complicated training process. In this paper, a plug-and-play LSTM-based Attention Module(LAM) is proposed to enhance flexibility of the multi-attention mechanism. First, we employ the single-stage multi-attention structure to replace the traditional multi-stage multi-attention structure. Our structure encapsulates multiple attention machines in single module and thus the module can be added to any backbone networks without any modification directly. Then, correlation is introduced to spatial attention machines through LSTM. Correlation between different attention machines preserves diversity of the local feature and exploit the capacity of multi-attention mechanism. Moreover, the LAM is added to the backbone network in the form of residual, which enables the LAM to be trained with the backbone network synchronously. Therefore, the training process is simplified effectively. Experiments on CUHK03, Market-1501 and DukeMTMC-ReID datasets demonstrate the advantage of the proposed method.

Paper Details

Date Published: 3 January 2020
PDF: 7 pages
Proc. SPIE 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), 113730C (3 January 2020); doi: 10.1117/12.2557241
Show Author Affiliations
Zhengxin Zeng, Beijing Univ. of Posts and Telecommunications (China)
Zhuqing Jiang, Beijing Univ. of Posts and Telecommunications (China)
Aidong Men, Beijing Univ. of Posts and Telecommunications (China)
Guodong Ju, GuangDong TUS-TuWei Technology Co., Ltd. (China)

Published in SPIE Proceedings Vol. 11373:
Eleventh International Conference on Graphics and Image Processing (ICGIP 2019)
Zhigeng Pan; Xun Wang, Editor(s)

© SPIE. Terms of Use
Back to Top