Autoregressive Visual Tracking

作者：Xing Wei, Yifan Bai, Yongchao Zheng, Dahu Shi, Yihong Gong · 年份：2023 · DOI：10.1109/cvpr52729.2023.00935 · 被引用次数：347 · 研究领域：Video Surveillance and Tracking Methods、Human Pose and Action Recognition、Advanced Vision and Imaging

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.