Video-Based Person Re-Identification by Simultaneously Learning Intra-Video and Inter-Video Distance Metrics

Xiaoke Zhu, Xiao-Yuan Jing, Xinge You, Xinyu Zhang, Taiping ZhangIEEE TIP 2018 · OpenReview

Abstract

Video-based person re-identification (re-id) is an important application in practice. Since large variations exist between different pedestrian videos, as well as within each video, it is challenging to conduct re-id between the pedestrian videos. In this paper, we propose a simultaneous intra-video and inter-video distance learning (SI <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> DL) approach for the video-based person re-id. Specifically, SI <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> DL simultaneously learns an intra-video distance metric and an inter-video distance metric from the training videos. The intra-video distance metric is used to make each video more compact, and the inter-video one is used to ensure that the distance between truly matching videos is smaller than that between wrong matching videos. Considering that the goal of distance learning is to make truly matching video pairs from different persons be well separated with each other, we also propose a pair separation-based SI <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> DL (P-SI <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> DL). P-SI <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> DL aims to learn a pair of distance metrics, under which any two truly matching video pairs can be well separated. Experiments on four public pedestrian image sequence data sets show that our approaches achieve the state-of-the-art performance.
BibTeX
@article{zhu2018video,
  author = {Xiaoke Zhu and Xiao-Yuan Jing and Xinge You and Xinyu Zhang and Taiping Zhang},
  title = {{Video-Based Person Re-Identification by Simultaneously Learning Intra-Video and Inter-Video Distance Metrics}},
  journal = {IEEE Trans. Image Process.},
  year = {2018},
  url = {https://openreview.net/forum?id=c45rT9bCCB0m},
}

Loading related content...

Figure