CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features

TL;DR

CSTrack introduces a novel approach for RGB-X tracking by modeling compact spatiotemporal features, simplifying the architecture, reducing computational overhead, and achieving state-of-the-art results on benchmarks.

Contribution

The paper proposes a new tracker with a Spatial Compact Module and a Temporal Compact Module for efficient and effective spatiotemporal feature modeling in RGB-X tracking.

Findings

Achieves new state-of-the-art results on RGB-X benchmarks.

Reduces computational complexity compared to existing methods.

Effectively models intra- and inter-modality spatial and temporal features.

Abstract

Effectively modeling and utilizing spatiotemporal features from RGB and other modalities (\eg, depth, thermal, and event data, denoted as X) is the core of RGB-X tracker design. Existing methods often employ two parallel branches to separately process the RGB and X input streams, requiring the model to simultaneously handle two dispersed feature spaces, which complicates both the model structure and computation process. More critically, intra-modality spatial modeling within each dispersed space incurs substantial computational overhead, limiting resources for inter-modality spatial modeling and temporal modeling. To address this, we propose a novel tracker, CSTrack, which focuses on modeling Compact Spatiotemporal features to achieve simple yet effective tracking. Specifically, we first introduce an innovative Spatial Compact Module that integrates the RGB-X dual input streams into a compact spatial feature, enabling thorough intra- and inter-modality spatial modeling. Additionally, we design an efficient Temporal Compact Module that compactly represents temporal features by constructing the refined target distribution heatmap. Extensive experiments validate the effectiveness of our compact spatiotemporal modeling method, with CSTrack achieving new SOTA results on mainstream RGB-X benchmarks. The code and models will be released at: https://github.com/XiaokunFeng/CSTrack.