EUVIMEDEUVIMED entdecken
Crossref

Multi-Prompts Learning with Cross-Modal Alignment for Attribute-Based Person Re-identification

Yajing Zhai, Yawen Zeng, Zhiyong Huang, Zheng Qin, Xin Jin, Da Cao

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (7) · 6979-6987

DOI: 10.1609/aaai.v38i7.28524 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Yajing Zhai und 5 weiteren Autor:innen. Die Arbeit wurde bisher 47-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The fine-grained attribute descriptions can significantly supplement the valuable semantic information for person image, which is vital to the success of person re-identification (ReID) task. However, current ReID algorithms typically failed to effectively leverage the rich contextual information available, primarily due to their reliance on simplistic and coarse utilization of image attributes. Recent advances in artificial intelligence generated content have made it possible to automatically generate plentiful fine-grained attribute descriptions and make full use of them. Thereby, this paper explores the potential of using the generated multiple person attributes as prompts in ReID tasks with off-the-shelf (large) models for more accurate retrieval results. To this end, we present a new framework called Multi-Prompts ReID (MP-ReID), based on prompt learning and language models, to fully dip fine attributes to assist ReID task. Specifically, MP-ReID first learns to hallucinate diverse, informative, and promptable sentences for describing the query images. This procedure includes (i) explicit prompts of which attributes a person has and furthermore (ii) implicit learnable prompts for adjusting/conditioning the criteria used towards this person identity matching. Explicit prompts are obtained by ensembling generation models, such as ChatGPT and VQA models. Moreover, an alignment module is designed to fuse multi-prompts (i.e., explicit and implicit ones) progressively and mitigate the cross-modal gap. Extensive experiments on the existing attribute-involved ReID datasets, namely, Market1501 and DukeMTMC-reID, demonstrate the effectiveness and rationality of the proposed MP-ReID solution.

Zitieren

APA

Zhai, Y., Zeng, Y., Huang, Z., Qin, Z., Jin, X., & Cao, D. (2024). Multi-Prompts Learning with Cross-Modal Alignment for Attribute-Based Person Re-identification. Proceedings of the AAAI Conference on Artificial Intelligence, 38(7), 6979-6987. https://doi.org/10.1609/aaai.v38i7.28524

Vancouver

Zhai Y, Zeng Y, Huang Z, Qin Z, Jin X, Cao D. Multi-Prompts Learning with Cross-Modal Alignment for Attribute-Based Person Re-identification. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(7):6979-6987. doi:10.1609/aaai.v38i7.28524

BibTeX
@article{Zhai2024,
  author = {Zhai, Yajing and Zeng, Yawen and Huang, Zhiyong and Qin, Zheng and Jin, Xin and Cao, Da},
  title = {Multi-Prompts Learning with Cross-Modal Alignment for Attribute-Based Person Re-identification},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {7},
  pages = {6979--6987},
  doi = {10.1609/aaai.v38i7.28524}
}
Kostenlos starten →