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

TL;DR

This paper introduces a multi-granular hypergraph framework for video-based person re-identification, effectively modeling spatiotemporal dependencies at multiple levels to improve accuracy and robustness.

Contribution

It proposes a novel hypergraph-based method that captures multi-granular spatial and temporal features, addressing misalignment and occlusion issues in video re-ID.

Findings

Achieves 90.0% top-1 accuracy on MARS dataset.

Outperforms state-of-the-art methods in video re-ID.

Demonstrates effectiveness of multi-granular hypergraph modeling.

Abstract

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.