Event-Adaptive State Transition and Gated Fusion for RGB-Event Object Tracking

TL;DR

MambaTrack is a novel RGB-Event tracking framework that adaptively modulates state transitions and fuses modalities using event density-aware gates, improving robustness and real-time applicability.

Contribution

It introduces an event-adaptive state transition mechanism and a gated fusion module, enhancing cross-modal fusion robustness in RGB-Event tracking.

Findings

Achieves state-of-the-art results on FE108 and FELT datasets.

Demonstrates robustness across varying event sparsity conditions.

Designed for real-time embedded deployment.

Abstract

Existing Vision Mamba-based RGB-Event(RGBE) tracking methods suffer from using static state transition matrices, which fail to adapt to variations in event sparsity. This rigidity leads to imbalanced modeling-underfitting sparse event streams and overfitting dense ones-thus degrading cross-modal fusion robustness. To address these limitations, we propose MambaTrack, a multimodal and efficient tracking framework built upon a Dynamic State Space Model(DSSM). Our contributions are twofold. First, we introduce an event-adaptive state transition mechanism that dynamically modulates the state transition matrix based on event stream density. A learnable scalar governs the state evolution rate, enabling differentiated modeling of sparse and dense event flows. Second, we develop a Gated Projection Fusion(GPF) module for robust cross-modal integration. This module projects RGB features into the event feature space and generates adaptive gates from event density and RGB confidence scores. These gates precisely control the fusion intensity, suppressing noise while preserving complementary information. Experiments show that MambaTrack achieves state-of-the-art performance on the FE108 and FELT datasets. Its lightweight design suggests potential for real-time embedded deployment.