Co-Saliency Spatio-Temporal Interaction Network for Person Re-Identification in Videos

TL;DR

This paper introduces CSTNet, a novel network that leverages co-saliency and spatial-temporal interactions to improve person re-identification accuracy in videos by focusing on salient regions and modeling long-range dependencies.

Contribution

The paper proposes a new CSTNet architecture with co-saliency learning and spatial-temporal interaction modules for enhanced video-based person re-identification.

Findings

CSTNet outperforms existing methods on benchmark datasets.

The co-saliency modules effectively focus on relevant pedestrian regions.

Spatial-temporal modules improve feature discrimination.

Abstract

Person re-identification aims at identifying a certain pedestrian across non-overlapping camera networks. Video-based re-identification approaches have gained significant attention recently, expanding image-based approaches by learning features from multiple frames. In this work, we propose a novel Co-Saliency Spatio-Temporal Interaction Network (CSTNet) for person re-identification in videos. It captures the common salient foreground regions among video frames and explores the spatial-temporal long-range context interdependency from such regions, towards learning discriminative pedestrian representation. Specifically, multiple co-saliency learning modules within CSTNet are designed to utilize the correlated information across video frames to extract the salient features from the task-relevant regions and suppress background interference. Moreover, multiple spatialtemporal interaction modules within CSTNet are proposed, which exploit the spatial and temporal long-range context interdependencies on such features and spatial-temporal information correlation, to enhance feature representation. Extensive experiments on two benchmarks have demonstrated the effectiveness of the proposed method.