EUVIMEDEUVIMED entdecken
Crossref

Dual-stream Relation-modeling Disentanglement for Cloth-Changing Person Re-Identification

Shijuan Huang, Hefei Ling, Zongyi Li, Xu Li, Zhao Lv

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5104-5112

DOI: 10.1609/aaai.v40i7.37424 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shijuan Huang und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cloth-changing person re-identification (CC-ReID) aims to identify individuals across non-overlapping cameras despite clothing variations. Existing methods are often constrained by two primary limitations: approaches using auxiliary modalities typically rely on a single specific cue, limiting their robustness, while feature disentanglement methods struggle with discrete labels that create inconsistencies between ground truth labels and modality semantic similarity. To overcome these limitations, we propose DRDnet, a unified framework that synergistically integrates dual auxiliary cues and advanced relation modeling. Specifically, our Dual-Stream Disentanglement (DSD) module leverages textual descriptions and parsing images to decouple clothing factors through high-level semantic supervision and pixel-level operations, yielding robust clothing-agnostic features. Simultaneously, our Modal Relation Modeling (MRM) module constructs feature memory banks and employs adaptive soft label smoothing, effectively enhancing image-text semantic alignment and reinforcing identity consistency across clothing changes. We evaluate DRDnet on several CC-ReID benchmarks to demonstrate its effectiveness and provide state-of-the-art performance across all benchmarks.

Zitieren

APA

Huang, S., Ling, H., Li, Z., Li, X., & Lv, Z. (2026). Dual-stream Relation-modeling Disentanglement for Cloth-Changing Person Re-Identification. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5104-5112. https://doi.org/10.1609/aaai.v40i7.37424

Vancouver

Huang S, Ling H, Li Z, Li X, Lv Z. Dual-stream Relation-modeling Disentanglement for Cloth-Changing Person Re-Identification. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5104-5112. doi:10.1609/aaai.v40i7.37424

BibTeX
@article{Huang2026,
  author = {Huang, Shijuan and Ling, Hefei and Li, Zongyi and Li, Xu and Lv, Zhao},
  title = {Dual-stream Relation-modeling Disentanglement for Cloth-Changing Person Re-Identification},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {7},
  pages = {5104--5112},
  doi = {10.1609/aaai.v40i7.37424}
}
Kostenlos starten →