Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2896-2905
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.Keywords
All Related Versions
This publication has 45 references indexed in Scilit:
- MARS: A Video Benchmark for Large-Scale Person Re-Identification2016
- Scalable Person Re-identification: A Benchmark2015
- Person Re-Identification with Discriminatively Trained Viewpoint Invariant Dictionaries2015
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- Person Re-identification by Video Ranking2014
- 3D Convolutional Neural Networks for Human Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008
- A Spatio-Temporal Descriptor Based on 3D-Gradients2008
- A 3-dimensional sift descriptor and its application to action recognition2007
- Person Reidentification Using Spatiotemporal Appearance2006