Vision Transformer based Random Walk for Group Re-Identification

TL;DR

This paper introduces a vision transformer-based random walk framework for group re-identification that effectively handles group layout changes and camera distance variations, outperforming existing methods.

Contribution

The paper proposes a novel vision transformer and random walk approach that considers camera distance and group layout changes for improved group re-ID.

Findings

Outperforms most existing methods in experiments

Effectively handles group layout and membership changes

Utilizes monocular depth estimation for graph construction

Abstract

Group re-identification (re-ID) aims to match groups with the same people under different cameras, mainly involves the challenges of group members and layout changes well. Most existing methods usually use the k-nearest neighbor algorithm to update node features to consider changes in group membership, but these methods cannot solve the problem of group layout changes. To this end, we propose a novel vision transformer based random walk framework for group re-ID. Specifically, we design a vision transformer based on a monocular depth estimation algorithm to construct a graph through the average depth value of pedestrian features to fully consider the impact of camera distance on group members relationships. In addition, we propose a random walk module to reconstruct the graph by calculating affinity scores between target and gallery images to remove pedestrians who do not belong to the current group. Experimental results show that our framework is superior to most methods.