Translator Disclaimer
3 January 2020 Video-based person re-identification with parallel spatial–temporal attention module
Author Affiliations +

We propose a parallel network with spatial–temporal attention for video-based person re-identification. Many previous video-based person re-identification methods use two-dimensional convolutional neural networks to extract spatial features, then, temporal features are extracted by temporal pooling or recurrent neural networks. Unfortunately, these series networks will cause the loss of spatial information when extracting temporal information. Different from previous methods, our parallel network can extract temporal and spatial features simultaneously, which can effectively reduce the loss of space information. In addition, we design a global temporal attention module, which obtains the attention weight through the correlation between the current frame and all the frames in the sequence. At the same time, the temporal module can act on the information extraction of spatial module. In this way, we can increase the temporal and spatial constraints. Experiments show that our method can effectively improve the re-id accuracy, better than the state-of-the-art methods.

© 2020 SPIE and IS&T 1017-9909/2020/$28.00 © 2020 SPIE and IS&T
Jun Kong, Zhende Teng, Min Jiang, and Hongtao Huo "Video-based person re-identification with parallel spatial–temporal attention module," Journal of Electronic Imaging 29(1), 013001 (3 January 2020).
Received: 6 August 2019; Accepted: 13 December 2019; Published: 3 January 2020


Gait recognition based on optimized neural network
Proceedings of SPIE (August 09 2018)
Robust 3D object model reconstruction from video
Proceedings of SPIE (April 16 2004)

Back to Top