EUVIMEDEUVIMED entdecken
Crossref

UniSOT: A Unified Framework for Multi-Modality Single Object Tracking

Yinchao Ma, Yuyang Tang, Wenfei Yang, Tianzhu Zhang, Xu Zhou, Feng Wu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-02 · 48 (2) · 1554-1572

DOI: 10.1109/tpami.2025.3615714 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-02. Verfasst von Yinchao Ma und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 116 Literaturangaben. Gefördert von: Youth Innovation Promotion Association of CAS, National Natural Science Foundation of China, Graduate School Special Funding Program of the University of Science and Technology of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single object tracking aims to localize target object with specific reference modalities (bounding box, natural language or both) in a sequence of specific video modalities (RGB, RGB+Depth, RGB+Thermal or RGB+Event.). Different reference modalities enable various human-machine interactions, and different video modalities are demanded in complex scenarios to enhance tracking robustness. Existing trackers are designed for single or several video modalities with single or several reference modalities, which leads to separate model designs and limits practical applications. Practically, a unified tracker is needed to handle various requirements. To the best of our knowledge, there is still no tracker that can perform tracking with these above reference modalities across these video modalities simultaneously. Thus, in this paper, we present a unified tracker, UniSOT, for different combinations of three reference modalities and four video modalities with uniform parameters. Extensive experimental results on 18 visual tracking, vision-language tracking and RGB+X tracking benchmarks demonstrate that UniSOT shows superior performance against modality-specific counterparts. Notably, UniSOT outperforms previous counterparts by over 3.0% AUC on TNL2K across all three reference modalities and outperforms Un-Track by over 2.0% main metric across all three RGB+X video modalities.

Förderung

  • Youth Innovation Promotion Association of CAS
  • National Natural Science Foundation of China
  • Graduate School Special Funding Program of the University of Science and Technology of China

Zitieren

APA

Ma, Y., Tang, Y., Yang, W., Zhang, T., Zhou, X., & Wu, F. (2026). UniSOT: A Unified Framework for Multi-Modality Single Object Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(2), 1554-1572. https://doi.org/10.1109/tpami.2025.3615714

Vancouver

Ma Y, Tang Y, Yang W, Zhang T, Zhou X, Wu F. UniSOT: A Unified Framework for Multi-Modality Single Object Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(2):1554-1572. doi:10.1109/tpami.2025.3615714

BibTeX
@article{Ma2026,
  author = {Ma, Yinchao and Tang, Yuyang and Yang, Wenfei and Zhang, Tianzhu and Zhou, Xu and Wu, Feng},
  title = {UniSOT: A Unified Framework for Multi-Modality Single Object Tracking},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {2},
  pages = {1554--1572},
  doi = {10.1109/tpami.2025.3615714}
}
Kostenlos starten →