TY - GEN
T1 - Autoregressive Visual Tracking
AU - Wei, Xing
AU - Bai, Yifan
AU - Zheng, Yongchao
AU - Shi, Dahu
AU - Gong, Yihong
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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. Source code is available at https://github.com/MIV-XJTU/ARTrack.
AB - 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. Source code is available at https://github.com/MIV-XJTU/ARTrack.
KW - Video: Low-level analysis
KW - and tracking
KW - motion
UR - https://www.scopus.com/pages/publications/85168211187
U2 - 10.1109/CVPR52729.2023.00935
DO - 10.1109/CVPR52729.2023.00935
M3 - 会议稿件
AN - SCOPUS:85168211187
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 9697
EP - 9706
BT - Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
PB - IEEE Computer Society
T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
Y2 - 18 June 2023 through 22 June 2023
ER -