Multi-level and multi-scale horizontal pooling network for person re-identification

Yunzhou Zhang, Shuangwei Liu, Lin Qi, Sonya Coleman, Dermot Kerr, Weidong Shi

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
5 Downloads (Pure)


Person re-identification (Re-ID) is the task of matching a target person across different cameras, which has drawn extensive attention in computer vision and has become an essential component in the video surveillance system. Despite recent remarkable progress, person re-identification methods are either subject to the power of feature representation, or give equal importance to all examples. To mitigate these issues, we introduce a simple, yet effective, Multi-level and Multi-scale Horizontal Pooling Network (MMHPN) for person re-identification. Concretely, our contributions are three-fold:1) we take partial feature representation into account at different pooling scales and different semantic levels so that various partial information is obtained to form a robust descriptor; 2) we introduce a Part Sensitive Loss (PSL) to reduce the effect of easily classified partition to facilitate training of the person re-identification network, 3) we conduct extensive experimental results using the Market-1501, DukeMTMC-reID and CUHK03 datasets and achieve mAP scores of 83.4%, 75.1% and 65.4% respectively on these challenging datasets.

Original languageEnglish
Pages (from-to)28603-28619
Number of pages17
JournalMultimedia Tools and Applications
Issue number39-40
Early online date5 Aug 2020
Publication statusPublished - 31 Oct 2020


  • Horizontal pooling network
  • Multi-level and multi-scale
  • Part sensitive loss
  • Person re-identification


Dive into the research topics of 'Multi-level and multi-scale horizontal pooling network for person re-identification'. Together they form a unique fingerprint.

Cite this