Video Person Re-identification using Attribute-enhanced Features

TL;DR

This paper introduces ASA-Net, a novel network for video person re-identification that leverages attribute-enhanced features and attention mechanisms to improve accuracy by focusing on salient regions and invariant attributes.

Contribution

The work proposes a new network architecture that uses attribute salience and a novel triplet loss to enhance video person Re-ID performance, addressing background separation and view/movement variations.

Findings

Significant improvement over existing methods in accuracy.

Effective attention on pedestrian body regions.

Robustness to view angle and movement variations.

Abstract

Video-based person re-identification (Re-ID) which aims to associate people across non-overlapping cameras using surveillance video is a challenging task. Pedestrian attribute, such as gender, age and clothing characteristics contains rich and supplementary information but is less explored in video person Re-ID. In this work, we propose a novel network architecture named Attribute Salience Assisted Network (ASA-Net) for attribute-assisted video person Re-ID, which achieved considerable improvement to existing works by two methods.First, to learn a better separation of the target from background, we propose to learn the visual attention from middle-level attribute instead of high-level identities. The proposed Attribute Salient Region Enhance (ASRE) module can attend more accurately on the body of pedestrian. Second, we found that many identity-irrelevant but object or subject-relevant factors like the view angle and movement of the target pedestrian can greatly influence the two dimensional appearance of a pedestrian. This problem can be mitigated by investigating both identity-relevant and identity-irrelevant attributes via a novel triplet loss which is referred as the Pose~\&~Motion-Invariant (PMI) triplet loss.