Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification

About

Video-based person re-identification (re-ID) is an important research topic in computer vision. The key to tackling the challenging task is to exploit both spatial and temporal clues in video sequences. In this work, we propose a novel graph-based framework, namely Multi-Granular Hypergraph (MGH), to pursue better representational capabilities by modeling spatiotemporal dependencies in terms of multiple granularities. Specifically, hypergraphs with different spatial granularities are constructed using various levels of part-based features across the video sequence. In each hypergraph, different temporal granularities are captured by hyperedges that connect a set of graph nodes (i.e., part-based features) across different temporal ranges. Two critical issues (misalignment and occlusion) are explicitly addressed by the proposed hypergraph propagation and feature aggregation schemes. Finally, we further enhance the overall video representation by learning more diversified graph-level representations of multiple granularities based on mutual information minimization. Extensive experiments on three widely adopted benchmarks clearly demonstrate the effectiveness of the proposed framework. Notably, 90.0% top-1 accuracy on MARS is achieved using MGH, outperforming the state-of-the-arts. Code is available at https://github.com/daodaofr/hypergraph_reid.

Yichao Yan, Jie Qin1, Jiaxin Chen, Li Liu, Fan Zhu, Ying Tai, Ling Shao• 2021

Related benchmarks

TaskDatasetResultRank
Video Person Re-IDMARS
Rank-1 Acc90
106
Video Person Re-IDiLIDS-VID
Rank-185.6
80
Person Re-IdentificationMARS (test)
Rank-190
72
Person Re-IdentificationPRID 2011 (test)
Rank-194.8
48
Video Person Re-IdentificationMARS (test)
Rank-190
35
Video Person Re-IdentificationG2A-VReID Ground to Aerial
mAP76.7
25
Video Person Re-IdentificationiLIDS-VID (test)
Rank-185.6
25
Video Person Re-IdentificationAG-VPReID Aerial to Ground
mAP60.3
20
Video-based Person Re-identificationDukeV
R195.3
15
Video Person Re-IdentificationLS-VID Ground to Ground
mAP61.8
14
Showing 10 of 13 rows

Other info

Code

Follow for update