Visual object tracking using learnable target-aware token emphasis

doi:10.1016/j.engappai.2025.110482

Return

Visual object tracking using learnable target-aware token emphasis

2025-06-01

PRE

Minho Park

Jinjoo Song

Sang Min Yoon *

DOI：10.1016/j.engappai.2025.110482

Original

Original request for help

Save

Abstract

En 中文

Visual object tracking, which involves tracking the spatial location of a target object either within a single viewpoint or across various camera perspectives, is an important task in computer vision. Deep neural networks, especially vision transformers, typically outperform traditional methods and have thus become the preferred choice for visual object tasks. However, existing visual object tracking frameworks still struggle to adapt to targets with continuously changing appearances within the current frame, as they rely heavily on the static initial target template rather than continuously emphasizing the evolving target features. In this paper, we introduce a visual object tracking network with a learnable target-aware token emphasis, which is composed of vision transformer backbone embedded in the token emphasizer, localization head and target template update decision module. The learnable target-aware token emphasizer and target template update decision modules in the proposed model contribute to stabilizing visual object tracking across various scenarios. This is achieved not only by emphasizing features that have a relationship between the target template and the search region but also by reducing irrelevant features and consistently updating the high-quality target template online during the process. Qualitative and quantitative analyses, including ablation analysis across a diverse set of tracking benchmark datasets, validate the robustness of the proposed tracking framework. The code and trained models are available at https://github.com/qkdkralsgh/TETrack.

Keywords:

Visual object tracking

Target aware token emphasis

Unified tracking model