ASDTracker: Adaptively Sparse Detection With Attention-Guided Refinement for Efficient Multi-Object Tracking

doi:10.1109/TIP.2026.3662594

ASDTracker: Adaptively Sparse Detection With Attention-Guided Refinement for Efficient Multi-Object Tracking

2026-02-13

0

PRE

AI

DOI：10.1109/TIP.2026.3662594

Original

Original request for help

Save

Abstract

En 中文

Tracking-by-Detection paradigms shine in generic multi-object tracking (MOT), while their compact construction hinders the real-time applications. In this work, we attribute the substantial computational burden to two expensive components, i.e. detection and re-identification. Building upon the principle of adaptively maintaining acceptable inference efficiency, we present Adaptively Sparse Detection with attention-guided refinement (ASDTracker) for efficient tracking. In specific, our ASDTracker rapidly assess the short-term and long-term occlusion, dynamically determining the usage of the expensive detector. For non-key frames, we efficiently refine small-size crops out of Kalman Filter predictions and introduce the noisy shadow labels to robustly train this refinement network. Additionally, we substitute the lightweight appearance representation for the heavy ReID network, which efficiently extracts sufficient appearance cues in the coarsely quantized color spaces. Extensive experiments on four benchmarks demonstrate that ASDTracker achieves competitive performance in generalization and robustness under favorable inference speed. Moreover, the efficient tracking deployment is further implemented to an unmanned surface vehicle with high accuracy and low latency in real-world scenarios.

Keywords:

Multi-object tracking

sparse detection

key-frame selection

attention-guided refinement

data association

ASDTracker: Adaptively Sparse Detection With Attention-Guided Refinement for Efficient Multi-Object Tracking

Abstract

Journal

Organization