Autoregressive Visual Tracking

Xing Wei, Yifan Bai, Yongchao Zheng, Dahu Shi, Yihong Gong

CVPR 2023 pp. 9697-9706

doi:10.1109/CVPR52729.2023.00935 /cvpr/2023/wei2023cvpr-autoregressive/

Abstract

We present ARTrack, an autoregressive framework for visual object tracking. ARTrack tackles tracking as a coordinate sequence interpretation task that estimates object trajectories progressively, where the current estimate is induced by previous states and in turn affects subsequences. This time-autoregressive approach models the sequential evolution of trajectories to keep tracing the object across frames, making it superior to existing template matching based trackers that only consider the per-frame localization accuracy. ARTrack is simple and direct, eliminating customized localization heads and post-processings. Despite its simplicity, ARTrack achieves state-of-the-art performance on prevailing benchmark datasets.

PDF CVPR Semantic Scholar

Cite

Text

Wei et al. "Autoregressive Visual Tracking." Conference on Computer Vision and Pattern Recognition, 2023. doi:10.1109/CVPR52729.2023.00935

Markdown

[Wei et al. "Autoregressive Visual Tracking." Conference on Computer Vision and Pattern Recognition, 2023.](https://mlanthology.org/cvpr/2023/wei2023cvpr-autoregressive/) doi:10.1109/CVPR52729.2023.00935

BibTeX

@inproceedings{wei2023cvpr-autoregressive,
  title     = {{Autoregressive Visual Tracking}},
  author    = {Wei, Xing and Bai, Yifan and Zheng, Yongchao and Shi, Dahu and Gong, Yihong},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2023},
  pages     = {9697-9706},
  doi       = {10.1109/CVPR52729.2023.00935},
  url       = {https://mlanthology.org/cvpr/2023/wei2023cvpr-autoregressive/}
}