Cross-Modal Alignment Enhancement Network for Text-to-Image Person Re-Identification

With the proliferation of visual Internet of Things (VIoT), the intelligent processing of imagery and textual data to accomplish text-to-image person re-identification (Re-ID) constitutes a formidable challenge within VIoT, where text-to-image person Re-ID endeavors to execute image retrieval across disparate visual sensors through designated text query. The existing works mainly focus on learning feature alignment between texts and images from global and local perspectives. However, these methods exhibit two fundamental limitations: 1) neglecting the relationship between different kinds of positive pairs (i.e., original positive pairs and weak positive pairs) during global feature alignment; 2) employing horizontally partitioned stripe parts of pedestrian images for local feature alignment constrains adaptability. To address these issues, we propose a novel cross-modal Alignment Enhancement Network (AENet), which effectively align cross-modal features by modeling the relationships among different positive pairs and enabling flexible local correspondences. Specifically, we design a Hybrid Positive Pair Learning (HPPL) strategy to fully exploit the complementary semantic information in original and weak positive pairs through adaptive fusion, thereby enhancing global feature alignment. Regarding local feature alignment, we develop a Local Aggregation and Dynamic Matching (LADM) module to learn fine-grained correspondences through generating representative cross-modal local aggregation features and implementing dynamic matching mechanism. Correspondingly, we propose a Token Reconstruction Loss (TRL) to regulate the local aggregation process, thereby ensuring the quality of local aggregation features. Extensive experiments on three publicly available benchmarks verify the effectiveness and superiority of the proposed method, exemplified by achieving 76.48%, 68.34%, and 66.70% Rank-1 accuracy on CUHK-PEDES, ICFG-PEDES, and RSTPReid, respectively.