SSN3D: Self-Separated Network to Align Parts for 3D Convolution in Video Person Re-Identification

Authors

  • Xiaoke Jiang ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences Sensetime Group
  • Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences Shanghai AI Lab, Shanghai, China
  • Junjie Yan Sensetime Group
  • Qichen Li MIT
  • Wanrong Zheng Sensetime Group
  • Dapeng Chen Sensetime Group

Keywords:

Image and Video Retrieval

Abstract

Temporal appearance misalignment is a crucial problem in video person re-identification. The same part of person (e.g. head or hand) appearing on different locations in video sequence weakens its discriminative ability, especially when we apply standard temporal aggregation such as 3D convolution or LSTM. To address this issue, we propose Self-Separated network (SSN) to seek out the same parts in different images. As the name implies, SSN, if trained in an unsupervised strategy, guarantees the selected parts distinct. With a few samples of labeled parts to guide SSN training, this semi-supervised trained SSN seeks out the parts that are human-understandable within a frame and stable across a video snippet. Given the distinct and stable person parts, rather than performing aggregation on features, we then apply 3D convolution across different frames for person re-identification. This SSN + 3D pipeline, dubbed SSN3D, is proved to be efficient through extensive experiments on both synthetic and real data.

Downloads

Published

2021-05-18

How to Cite

Jiang, X., Qiao, Y., Yan, J., Li, Q., Zheng, W., & Chen, D. (2021). SSN3D: Self-Separated Network to Align Parts for 3D Convolution in Video Person Re-Identification. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1691-1699. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16262

Issue

Section

AAAI Technical Track on Computer Vision I