---
title: "Richer Semantics, Better Alignment: Aligning Visual Features with Explicit and Enriched Semantics for Visible-Infrared Person Re-Identification"
authors:
  - "Neng Dong"
  - "Shuanglin Yan"
  - "Liyan Zhang"
  - "Jinhui Tang"
doi: "10.24963/ijcai.2025/104"
url: "https://ijcai.org/proceedings/2025/104"
pdf: "https://ijcai.org/proceedings/2025/0104.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "927-935"
track: "Main Track"
keywords:
  - "Computer Vision: CV: Biomedical image analysis"
  - "Computer Vision: CV: Biometrics, face, gesture and pose recognition"
  - "Computer Vision: CV: Image and video retrieval"
  - "Computer Vision: CV: Machine learning for vision"
---

# Richer Semantics, Better Alignment: Aligning Visual Features with Explicit and Enriched Semantics for Visible-Infrared Person Re-Identification

Neng Dong, Shuanglin Yan, Liyan Zhang, Jinhui Tang

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 927-935. DOI: [10.24963/ijcai.2025/104](https://doi.org/10.24963/ijcai.2025/104)

## Abstract

Visible-infrared person re-identification (VIReID) retrieves pedestrian images with the same identity across different modalities. Existing methods learn visual features solely from images, failing to align them into the modality-invariant semantic space. In this paper, we propose a novel framework, termed Richer Semantics, Better Alignment (RSBA), to align visual features with explicit and enriched semantics. Specifically, we first develop an Explicit Semantics-Guided Feature Alignment (ESFA) module, which supplements textual descriptions for cross-modality images and aligns image-text pairs within each modality, alleviating the distribution discrepancy of visual features. We then devise a Consistent Similarity-Guided Indirect Alignment (CSIA) module, which constrains the similarity between intra-modality image-text pairs to be consistent with that between inter-modality text-text pairs, indirectly aligning visual features with cross-modality semantics. Furthermore, we design a Cross-View Semantics Compensation (CVSC) module, which integrates multi-view texts and improves the image-text matching of one-to-one in ESFA and CSIA to one-to-many, further strengthening the alignment of visual features within the semantic space. Extensive experimental results on three public datasets demonstrate the effectiveness and superiority of our proposed RSBA.