ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe
Preprint
Abstract
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.
Keywords
All Related Versions
This publication has 49 references indexed in Scilit:
- MOTR: End-to-End Multiple-Object Tracking with Transformer2022
- Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework2022
- Towards Sequence-Level Training for Visual Tracking2022
- Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking2022
- Ocean: Object-Aware Anchor-Free Tracking2020
- TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild2018
- Distractor-Aware Siamese Networks for Visual Object Tracking2018
- Learning Dynamic Memory Networks for Object Tracking2018
- A Benchmark and Simulator for UAV Tracking2016
- Microsoft COCO: Common Objects in Context2014