Multi-modal tracking is essential in single-object tracking (SOT), as different sensor types contribute unique capabilities to overcome challenges caused by variations in object appearance. However, existing unified RGB-X trackers (X represents depth, event, or thermal modality) either rely on the task-specific training strategy for individual RGB-X image pairs or fail to address the critical importance of modality-adaptive perception in real-world applications. In this work, we propose UASTrack, a unified adaptive selection framework that facilitates both model and parameter unification, as well as adaptive modality discrimination across various multi-modal tracking tasks. To achieve modality-adaptive perception in joint RGB-X pairs, we design a Discriminative Auto-Selector (DAS) capable of identifying modality labels, thereby distinguishing the data distributions of auxiliary modalities. Furthermore, we propose a Task-Customized Optimization Adapter (TCOA) tailored to various modalities in the latent space. This strategy effectively filters noise redundancy and mitigates background interference based on the specific characteristics of each modality. Extensive comparisons conducted on five benchmarks including LasHeR, GTOT, RGBT234, VisEvent, and DepthTrack, covering RGB-T, RGB-E, and RGB-D tracking scenarios, demonstrate our innovative approach achieves comparative performance by introducing only additional training parameters of 1.87M and flops of 1.95G. The code will be available at https://github.com/wanghe/UASTrack.

翻译：多模态跟踪在单目标跟踪（SOT）中至关重要，因为不同传感器类型具有独特能力，可克服目标外观变化带来的挑战。然而，现有的统一RGB-X跟踪器（X代表深度、事件或热成像模态）要么依赖针对各RGB-X图像对的特定任务训练策略，要么未能解决现实应用中模态自适应感知的关键重要性。本文提出UASTrack，一种统一的适应性选择框架，同时实现了模型与参数统一，以及跨各种多模态跟踪任务的自适应模态判别。为实现RGB-X联合对中的模态自适应感知，我们设计了能识别模态标签的判别式自动选择器（DAS），从而区分辅助模态的数据分布。此外，我们提出了针对隐空间中不同模态定制的任务优化适配器（TCOA）。该策略基于各模态的特定特性，有效滤除噪声冗余并减轻背景干扰。在涵盖RGB-T、RGB-E和RGB-D跟踪场景的五个基准数据集（包括LasHeR、GTOT、RGBT234、VisEvent和DepthTrack）上的广泛对比表明，我们的创新方法仅引入1.87M额外训练参数和1.95G FLOPs即可实现相当的性能。代码将开源至https://github.com/wanghe/UASTrack。