EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

A Survey on Text-to-Image Person Re-identification: From CLIP to Fine-Grained Cross-Modal Alignment

Dongbin Chen, Xiaohang Su, Junjie Li, Yancheng Wu, Shirun Liang

Advances in Engineering Research Possibilities and Challenges · 29.05.2026 · 4 (2) · 141

DOI: 10.63313/aerpc.9097 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advances in Engineering Research Possibilities and Challenges, online erschienen am 29.05.2026. Verfasst von Dongbin Chen und 4 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text-to-image person re-identification (TI-ReID) has become a critical task in intelligent surveillance, aiming to retrieve a target pedestrian from a large image gallery using a natural language description. Unlike image-based ReID, TI-ReID must bridge the semantic gap between modalities while capturing fine-grained, identity-discriminative details. The advent of Vision-Language Pre-training (VLP) models, particularly CLIP, has significantly advanced the field by providing robust pre-trained cross-modal representations. However, directly applying CLIP to TI-ReID is suboptimal due to a granularity gap: CLIP is effective at global scene-level matching, whereas TI-ReID demands fine-grained alignment of attributes like clothing, accessories, and actions. This survey systematically reviews the evolution of TI-ReID, from early unimodal backbone approaches to modern CLIP-based frameworks. We categorize existing methods into three main paradigms: 1) global feature learning with contrastive objectives, 2) part-level alignment using spatial attention or human parsers, and 3) token-level interaction and selection mechanisms. We analyze the core challenges of visual token redundancy, weak part-level correspondence, and noisy cross-modal data. Key representative methods such as IRRA, CFine, RASA, and RDE are discussed. Finally, we identify key open challenges and outline promising future directions, including multimodal large language models, query-aware alignment, and video-based ReID.

Zitieren

APA

Chen, D., Su, X., Li, J., Wu, Y., & Liang, S. (2026). A Survey on Text-to-Image Person Re-identification: From CLIP to Fine-Grained Cross-Modal Alignment. Advances in Engineering Research Possibilities and Challenges, 4(2), 141. https://doi.org/10.63313/aerpc.9097

Vancouver

Chen D, Su X, Li J, Wu Y, Liang S. A Survey on Text-to-Image Person Re-identification: From CLIP to Fine-Grained Cross-Modal Alignment. Advances in Engineering Research Possibilities and Challenges. 2026;4(2):141. doi:10.63313/aerpc.9097

BibTeX
@article{Chen2026,
  author = {Chen, Dongbin and Su, Xiaohang and Li, Junjie and Wu, Yancheng and Liang, Shirun},
  title = {A Survey on Text-to-Image Person Re-identification: From CLIP to Fine-Grained Cross-Modal Alignment},
  journal = {Advances in Engineering Research Possibilities and Challenges},
  year = {2026},
  volume = {4},
  number = {2},
  pages = {141},
  doi = {10.63313/aerpc.9097}
}
Kostenlos starten →