Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification

TL;DR

This paper introduces a novel joint spatial-temporal attention pooling network for video-based person re-identification, which adaptively focuses on important regions and frames, improving matching accuracy in surveillance scenarios.

Contribution

The proposed ASTPN model integrates spatial and temporal attention guided by matching information, enhancing feature extraction for person re-id over existing methods.

Findings

Outperforms state-of-the-art on iLIDS-VID, PRID-2011, MARS datasets

Joint pooling in space and time boosts re-id accuracy

Analysis confirms combined pooling is more effective than separate approaches

Abstract

Person Re-Identification (person re-id) is a crucial task as its applications in visual surveillance and human-computer interaction. In this work, we present a novel joint Spatial and Temporal Attention Pooling Network (ASTPN) for video-based person re-identification, which enables the feature extractor to be aware of the current input video sequences, in a way that interdependency from the matching items can directly influence the computation of each other's representation. Specifically, the spatial pooling layer is able to select regions from each frame, while the attention temporal pooling performed can select informative frames over the sequence, both pooling guided by the information from distance matching. Experiments are conduced on the iLIDS-VID, PRID-2011 and MARS datasets and the results demonstrate that this approach outperforms existing state-of-art methods. We also analyze how the joint pooling in both dimensions can boost the person re-id performance more effectively than using either of them separately.