EUVIMEDEUVIMED entdecken
Crossref

OmniTracker: Unifying Visual Object Tracking by Tracking-With-Detection

Junke Wang, Zuxuan Wu, Dongdong Chen, Chong Luo, Xiyang Dai, Lu Yuan, Yu-Gang Jiang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-04 · 47 (4) · 3159-3174

DOI: 10.1109/tpami.2025.3529926 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-04. Verfasst von Junke Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 146 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Visual Object Tracking (VOT) aims to estimate the positions of target objects in a video sequence, which is an important vision task with various real-world applications. Depending on whether the initial states of target objects are specified by provided annotations in the first frame or the categories, VOT could be classified as instance tracking (e.g., SOT and VOS) and category tracking (e.g., MOT, MOTS, and VIS) tasks. Different definitions have led to divergent solutions for these two types of tasks, resulting in redundant training expenses and parameter overhead. In this paper, combing the advantages of the best practices developed in both communities, we propose a novel tracking-with-detection paradigm, where tracking supplements appearance priors for detection and detection provides tracking with candidate bounding boxes for the association. Equipped with such a design, a unified tracking model, OmniTracker, is further presented to resolve all the tracking tasks with a fully shared network architecture, model weights, and inference pipeline, eliminating the need for task-specific architectures and reducing redundancy in model parameters. We conduct extensive experimentation on seven prominent tracking datasets of different tracking tasks, including LaSOT, TrackingNet, DAVIS16-17, MOT17, MOTS20, and YTVIS19, and demonstrate that OmniTracker achieves on-par or even better results than both task-specific and unified tracking models.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, J., Wu, Z., Chen, D., Luo, C., Dai, X., Yuan, L., & Jiang, Y. G. (2025). OmniTracker: Unifying Visual Object Tracking by Tracking-With-Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4), 3159-3174. https://doi.org/10.1109/tpami.2025.3529926

Vancouver

Wang J, Wu Z, Chen D, Luo C, Dai X, Yuan L, et al. OmniTracker: Unifying Visual Object Tracking by Tracking-With-Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(4):3159-3174. doi:10.1109/tpami.2025.3529926

BibTeX
@article{Wang2025,
  author = {Wang, Junke and Wu, Zuxuan and Chen, Dongdong and Luo, Chong and Dai, Xiyang and Yuan, Lu and Jiang, Yu-Gang},
  title = {OmniTracker: Unifying Visual Object Tracking by Tracking-With-Detection},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {4},
  pages = {3159--3174},
  doi = {10.1109/tpami.2025.3529926}
}
Kostenlos starten →