Adaptive Graph Representation Learning for Video Person Re-identification

TL;DR

This paper introduces an adaptive graph-based approach for video person re-identification that models part relations through an innovative graph structure and employs temporal regularization to improve feature discriminability.

Contribution

It proposes a novel adaptive graph representation learning scheme that captures part relations and a temporal resolution-aware regularization for enhanced video person Re-ID.

Findings

Achieves competitive results on four benchmark datasets.

Effectively models part relations using an adaptive graph structure.

Improves feature discriminability with temporal regularization.

Abstract

Recent years have witnessed the remarkable progress of applying deep learning models in video person re-identification (Re-ID). A key factor for video person Re-ID is to effectively construct discriminative and robust video feature representations for many complicated situations. Part-based approaches employ spatial and temporal attention to extract representative local features. While correlations between parts are ignored in the previous methods, to leverage the relations of different parts, we propose an innovative adaptive graph representation learning scheme for video person Re-ID, which enables the contextual interactions between relevant regional features. Specifically, we exploit the pose alignment connection and the feature affinity connection to construct an adaptive structure-aware adjacency graph, which models the intrinsic relations between graph nodes. We perform feature propagation on the adjacency graph to refine regional features iteratively, and the neighbor nodes' information is taken into account for part feature representation. To learn compact and discriminative representations, we further propose a novel temporal resolution-aware regularization, which enforces the consistency among different temporal resolutions for the same identities. We conduct extensive evaluations on four benchmarks, i.e. iLIDS-VID, PRID2011, MARS, and DukeMTMC-VideoReID, experimental results achieve the competitive performance which demonstrates the effectiveness of our proposed method. The code is available at https://github.com/weleen/AGRL.pytorch.