ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe
We present ARTrackV2, which integrates two pivotal aspects of tracking: determining where to look (localization) and how to describe (appearance analysis) the target object across video frames. Building on the foundation of its predecessor, ARTrackV2 extends the concept by introducing a unified generative framework to "read out" object's trajectory and "retell" its appearance in an autoregressive manner. This approach fosters a time-continuous methodology that models the joint evolution of motion and visual features, guided by previous estimates. Furthermore, ARTrackV2 stands out for its efficiency and simplicity, obviating the less efficient intra-frame autoregression and hand-tuned parameters for appearance updates. Despite its simplicity, ARTrackV2 achieves state-of-the-art performance on prevailing benchmark datasets while demonstrating remarkable efficiency improvement. In particular, ARTrackV2 achieves AO score of 79.5\% on GOT-10k, and AUC of 86.1\% on TrackingNet while being $3.6 \times$ faster than ARTrack. The code will be released.
PDF AbstractCode
Datasets
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Visual Object Tracking | GOT-10k | ARTrackV2-L | Average Overlap | 79.5 | # 1 | |
Success Rate 0.5 | 87.8 | # 1 | ||||
Success Rate 0.75 | 79.6 | # 1 | ||||
Visual Object Tracking | LaSOT | ARTrackV2-L | AUC | 73.6 | # 2 | |
Normalized Precision | 82.8 | # 1 | ||||
Precision | 81.1 | # 1 | ||||
Visual Object Tracking | LaSOT-ext | ARTrackV2-L | AUC | 53.4 | # 3 | |
Normalized Precision | 63.7 | # 2 | ||||
Precision | 60.2 | # 2 | ||||
Visual Object Tracking | NeedForSpeed | ARTrackV2-L | AUC | 0.684 | # 1 | |
Visual Object Tracking | TNL2K | ARTrackV2-L | AUC | 61.6 | # 2 | |
Visual Object Tracking | TrackingNet | ARTrackV2-L | Precision | 86.2 | # 2 | |
Normalized Precision | 90.4 | # 1 | ||||
Accuracy | 86.1 | # 1 | ||||
Visual Object Tracking | UAV123 | ARTrackV2-L | AUC | 0.717 | # 2 |