PSDiff: Diffusion Model for Person Search With Iterative and Collaborative Refinement
IEEE Transactions on Circuits and Systems for Video Technology · 2025-06 · 35 (6) · 5153-5165
DOI: 10.1109/tcsvt.2024.3524733 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-06. Verfasst von Chengyou Jia und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 101 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shaanxi Province, Key Research and Development Project in Shaanxi Province.
Abstract (Originalsprache)
Dominant Person Search methods aim to localize and recognize query persons in a unified network, which jointly optimizes the two sub-tasks of pedestrian detection and Re-Identification (ReID). Despite significant progress, current methods face two primary challenges: 1) the pedestrian candidates learned within detectors are suboptimal for the ReID task. 2) the potential for collaboration between two sub-tasks is overlooked. To address these issues, we present a novel Person Search framework based on the Diffusion model, PSDiff. PSDiff formulates the person search as a dual denoising process from noisy boxes and ReID embeddings to ground truths. Distinct from the conventional Detection-to-ReID approach, our denoising paradigm discards prior pedestrian candidates generated by detectors, thereby avoiding the local optimum problem of the ReID task. Following the new paradigm, we further design a new Collaborative Denoising Layer (CDL) to optimize detection and ReID sub-tasks in an iterative and collaborative way, which makes two sub-tasks mutually beneficial. Extensive experiments on the standard benchmarks show that PSDiff achieves state-of-the-art performance with fewer parameters and elastic computing overhead.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shaanxi Province
- Key Research and Development Project in Shaanxi Province
- Project of China Knowledge Center for Engineering Science and Technology
- Project of Chinese Academy of Engineering “The Online and Offline Mixed Educational Service System for “The Belt and Road” Training in MOOC China;”
- K. C. Wong Education Foundation
Zitieren
APA
Jia, C., Luo, M., Dang, Z., Dai, G., Chang, X., & Wang, J. (2025). PSDiff: Diffusion Model for Person Search With Iterative and Collaborative Refinement. IEEE Transactions on Circuits and Systems for Video Technology, 35(6), 5153-5165. https://doi.org/10.1109/tcsvt.2024.3524733
Vancouver
Jia C, Luo M, Dang Z, Dai G, Chang X, Wang J. PSDiff: Diffusion Model for Person Search With Iterative and Collaborative Refinement. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(6):5153-5165. doi:10.1109/tcsvt.2024.3524733
BibTeX
@article{Jia2025,
author = {Jia, Chengyou and Luo, Minnan and Dang, Zhuohang and Dai, Guang and Chang, Xiaojun and Wang, Jingdong},
title = {PSDiff: Diffusion Model for Person Search With Iterative and Collaborative Refinement},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {6},
pages = {5153--5165},
doi = {10.1109/tcsvt.2024.3524733}
}
EUVIMED