EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Scene-Prompt-Driven Dynamic Routing Expert Network for Open-World Person Re-Identification

Peng Dong, Hongbin Liu, Xiuyi Guo, Jilong Li, Yitong Zhou, Baoxu Wang

Mathematics · 31.07.2026 · 14 (15) · 2716

DOI: 10.3390/math14152716 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 31.07.2026. Verfasst von Peng Dong und 5 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shandong Province Natural Science Foundation, Key R&D Plan of Shandong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Open-world person re-identification (ReID) faces severe spatially asymmetric interferences, such as partial occlusion and illumination distortion. Existing models adopting static weight fusion irreversibly corrupt identity representations when processing localized noise. To address this, we propose a Scene-Prompt-Driven Dynamic Routing Expert Network (SPDR-Net). Guided by spatial topological prior constraints, SPDR-Net treats person semantic parts as independent local experts. First, a semantic expert module decouples and refines local features using human spatial topology priors. Second, a Prompt-Guided Dynamic Routing (PGDR) network extracts high-level scene contexts to dynamically evaluate each expert’s reliability, assigning routing weights to attenuate noise propagation. Finally, a global–local fusion module superimposes high-purity local features onto a global identity anchor, maintaining topological integrity to generate a unified descriptor for robust person re-identification. Extensive experiments on seven public benchmarks and a newly constructed real-world street dataset (SD-ReID) demonstrate that SPDR-Net achieves highly competitive performance against state-of-the-art methods and exhibits superior robustness under severe spatial-asymmetric interferences. Furthermore, end-to-end multi-camera closed-loop tests verify its robust decision-making capability and high engineering application value in real-world security systems.

Förderung

  • Shandong Province Natural Science Foundation
  • Key R&D Plan of Shandong Province

Zitieren

APA

Dong, P., Liu, H., Guo, X., Li, J., Zhou, Y., & Wang, B. (2026). Scene-Prompt-Driven Dynamic Routing Expert Network for Open-World Person Re-Identification. Mathematics, 14(15), 2716. https://doi.org/10.3390/math14152716

Vancouver

Dong P, Liu H, Guo X, Li J, Zhou Y, Wang B. Scene-Prompt-Driven Dynamic Routing Expert Network for Open-World Person Re-Identification. Mathematics. 2026;14(15):2716. doi:10.3390/math14152716

BibTeX
@article{Dong2026,
  author = {Dong, Peng and Liu, Hongbin and Guo, Xiuyi and Li, Jilong and Zhou, Yitong and Wang, Baoxu},
  title = {Scene-Prompt-Driven Dynamic Routing Expert Network for Open-World Person Re-Identification},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {15},
  pages = {2716},
  doi = {10.3390/math14152716}
}
Kostenlos starten →