EUVIMEDEUVIMED entdecken
Crossref

ODTrack: Online Dense Temporal Token Learning for Visual Tracking

Yaozong Zheng, Bineng Zhong, Qihua Liang, Zhiyi Mo, Shengping Zhang, Xianxian Li

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (7) · 7588-7596

DOI: 10.1609/aaai.v38i7.28591 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Yaozong Zheng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 240-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between reference and search frames via an offline mode. Consequently, they can only interact independently within each image-pair and establish limited temporal correlations. To alleviate the above problem, we propose a simple, flexible and effective video-level tracking pipeline, named ODTrack, which densely associates the contextual relationships of video frames in an online token propagation manner. ODTrack receives video frames of arbitrary length to capture the spatio-temporal trajectory relationships of an instance, and compresses the discrimination features (localization information) of a target into a token sequence to achieve frame-to-frame association. This new solution brings the following benefits: 1) the purified token sequences can serve as prompts for the inference in the next video frame, whereby past information is leveraged to guide future inference; 2) the complex online update strategies are effectively avoided by the iterative propagation of token sequences, and thus we can achieve more efficient model representation and computation. ODTrack achieves a new SOTA performance on seven benchmarks, while running at real-time speed. Code and models are available at https://github.com/GXNU-ZhongLab/ODTrack.

Zitieren

APA

Zheng, Y., Zhong, B., Liang, Q., Mo, Z., Zhang, S., & Li, X. (2024). ODTrack: Online Dense Temporal Token Learning for Visual Tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 38(7), 7588-7596. https://doi.org/10.1609/aaai.v38i7.28591

Vancouver

Zheng Y, Zhong B, Liang Q, Mo Z, Zhang S, Li X. ODTrack: Online Dense Temporal Token Learning for Visual Tracking. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(7):7588-7596. doi:10.1609/aaai.v38i7.28591

BibTeX
@article{Zheng2024,
  author = {Zheng, Yaozong and Zhong, Bineng and Liang, Qihua and Mo, Zhiyi and Zhang, Shengping and Li, Xianxian},
  title = {ODTrack: Online Dense Temporal Token Learning for Visual Tracking},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {7},
  pages = {7588--7596},
  doi = {10.1609/aaai.v38i7.28591}
}
Kostenlos starten →