UniSOT: A Unified Framework for Multi-Modality Single Object Tracking

TL;DR

UniSOT is a novel unified tracking framework capable of handling multiple reference and video modalities simultaneously, improving robustness and performance across diverse tracking scenarios.

Contribution

This paper introduces UniSOT, the first unified tracker that supports various reference and video modalities with a single model, enhancing practical applicability.

Findings

Outperforms modality-specific trackers on 18 benchmarks.

Achieves over 3.0% AUC improvement on TNL2K.

Surpasses Un-Track by over 2.0% across RGB+X modalities.

Abstract

Single object tracking aims to localize target object with specific reference modalities (bounding box, natural language or both) in a sequence of specific video modalities (RGB, RGB+Depth, RGB+Thermal or RGB+Event.). Different reference modalities enable various human-machine interactions, and different video modalities are demanded in complex scenarios to enhance tracking robustness. Existing trackers are designed for single or several video modalities with single or several reference modalities, which leads to separate model designs and limits practical applications. Practically, a unified tracker is needed to handle various requirements. To the best of our knowledge, there is still no tracker that can perform tracking with these above reference modalities across these video modalities simultaneously. Thus, in this paper, we present a unified tracker, UniSOT, for different combinations of three reference modalities and four video modalities with uniform parameters. Extensive experimental results on 18 visual tracking, vision-language tracking and RGB+X tracking benchmarks demonstrate that UniSOT shows superior performance against modality-specific counterparts. Notably, UniSOT outperforms previous counterparts by over 3.0\% AUC on TNL2K across all three reference modalities and outperforms Un-Track by over 2.0\% main metric across all three RGB+X video modalities.