Group Reidentification with Multigrained Matching and Integration

Weiyao Lin*, Yuxi Li, Hao Xiao, John See, Junni Zou, Hongkai Xiong, Jingdong Wang, Tao Mei

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

22 Citations (Scopus)


The task of reidentifying groups of people under different camera views is an important yet less-studied problem. Group reidentification (Re-ID) is a very challenging task since it is not only adversely affected by common issues in traditional single-object Re-ID problems, such as viewpoint and human pose variations, but also suffers from changes in group layout and group membership. In this paper, we propose a novel concept of group granularity by characterizing a group image by multigrained objects: individual people and subgroups of two and three people within a group. To achieve robust group Re-ID, we first introduce multigrained representations which can be extracted via the development of two separate schemes, that is, one with handcrafted descriptors and another with deep neural networks. The proposed representation seeks to characterize both appearance and spatial relations of multigrained objects, and is further equipped with importance weights which capture variations in intragroup dynamics. Optimal group-wise matching is facilitated by a multiorder matching process which, in turn, dynamically updates the importance weights in iterative fashion. We evaluated three multicamera group datasets containing complex scenarios and large dynamics, with experimental results demonstrating the effectiveness of our approach.

Original languageEnglish
Pages (from-to)1478-1492
Number of pages15
JournalIEEE Transactions on Cybernetics
Issue number3
Early online date11 Jun 2019
Publication statusPublished - Mar 2021


  • Group reidentification (Re-ID)
  • group-wise matching
  • multigrained representation
  • Re-ID

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Information Systems
  • Human-Computer Interaction
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Group Reidentification with Multigrained Matching and Integration'. Together they form a unique fingerprint.

Cite this