QA-ReID: Quality-Aware Query-Adaptive Convolution Leveraging Fused Global and Structural Cues for Clothes-Changing ReID
This addresses clothes-changing person re-identification, a challenging domain-specific problem with practical applications in surveillance, but it appears incremental as it builds on existing multi-modal fusion approaches.
The paper tackles the problem of person re-identification when clothing changes, proposing QA-ReID which fuses global appearance and structural cues with adaptive attention and matching techniques. It achieves state-of-the-art performance on multiple benchmarks like PRCC, LTCC, and VC-Clothes, significantly outperforming existing methods in cross-clothing scenarios.
Unlike conventional person re-identification (ReID), clothes-changing ReID (CC-ReID) presents severe challenges due to substantial appearance variations introduced by clothing changes. In this work, we propose the Quality-Aware Dual-Branch Matching (QA-ReID), which jointly leverages RGB-based features and parsing-based representations to model both global appearance and clothing-invariant structural cues. These heterogeneous features are adaptively fused through a multi-modal attention module. At the matching stage, we further design the Quality-Aware Query Adaptive Convolution (QAConv-QA), which incorporates pixel-level importance weighting and bidirectional consistency constraints to enhance robustness against clothing variations. Extensive experiments demonstrate that QA-ReID achieves state-of-the-art performance on multiple benchmarks, including PRCC, LTCC, and VC-Clothes, and significantly outperforms existing approaches under cross-clothing scenarios.