TDDiffDet: Temporal-density diffusion for sports video detection
PLOS One · 16.11.2026 · 21 (11) · e0353317
DOI: 10.1371/journal.pone.0353317 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 16.11.2026. Verfasst von Qi Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Physical Education, Xinyang Vocational and Technical College, Xinyang, China. Hauptthemen laut MEDLINE: Sports, Video Recording, Image Processing, Computer-Assisted. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Diffusion-based detection models formulate object detection as an iterative denoising process from noisy boxes to target bounding boxes, offering a promising paradigm for sports video object detection. However, two critical challenges remain. (1) Existing diffusion detectors perform frame-independent denoising from random noise, disregarding the temporal continuity inherent in video sequences, which causes detection results for the same target to exhibit spatial jitter across consecutive frames. (2) In densely crowded regions common in sports scenarios, the self-attention mechanism within the denoising decoder causes spatially adjacent proposal representations to progressively converge during iterative denoising, ultimately collapsing onto the same target location and resulting in missed detections. To address these issues, we propose TDDiffDet, a framework comprising two core modules: the Temporal Prior-guided Denoising module (TPDen) and the Density-Aware Decoupling module (DADec). TPDen leverages detection results from the previous frame as denoising initialization priors and injects inter-frame motion features into the conditioning pathway of the denoising network, enabling refinement from meaningful priors rather than pure noise, thereby improving temporal consistency while reducing redundant computation. DADec introduces a density-aware coupling suppression mechanism into the self-attention layers of the denoising decoder, dynamically attenuating attention associations between adjacent proposals in densely crowded regions to preserve the independence of each proposal’s denoising trajectory and prevent dense targets from being merged due to representation coupling. Extensive experiments on SportsMOT and SoccerNet-Tracking demonstrate that TDDiffDet achieves significant performance improvements over existing methods, validating the effectiveness of the proposed strategies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Physical Education, Xinyang Vocational and Technical College, Xinyang, China.
- Faculty of Social Sciences and Liberal Arts, UCSI University, Kuala Lumpur, Malaysia.
ORCID-Profile: Qi Liu, Chua Yan Piaw
Zitieren
APA
Liu, Q., Bailey, R. P., Yan Piaw, C., & Samsudin, N. (2026). TDDiffDet: Temporal-density diffusion for sports video detection. PLOS One, 21(11), e0353317. https://doi.org/10.1371/journal.pone.0353317
Vancouver
Liu Q, Bailey RP, Yan Piaw C, Samsudin N. TDDiffDet: Temporal-density diffusion for sports video detection. PLOS One. 2026;21(11):e0353317. doi:10.1371/journal.pone.0353317
BibTeX
@article{Liu2026,
author = {Liu, Qi and Bailey, Richard Peter and Yan Piaw, Chua and Samsudin, Nadia},
title = {TDDiffDet: Temporal-density diffusion for sports video detection},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {11},
pages = {e0353317},
doi = {10.1371/journal.pone.0353317}
}
EUVIMED