eMoE-Tracker: Environmental MoE-based Transformer for Robust Event-guided Object Tracking
Yucheng Chen, Lin Wang

TL;DR
eMoE-Tracker is a transformer-based framework that disentangles environmental attributes and enhances target-template interaction, achieving state-of-the-art performance in event-guided object tracking under challenging conditions.
Contribution
The paper introduces the environmental Mix-of-Experts (eMoE) module and contrastive relation modeling, enabling dynamic attribute-specific feature learning and improved target discrimination.
Findings
Outperforms prior methods on diverse benchmarks
Effectively handles challenging environmental conditions
Enhances target-template interaction through novel modules
Abstract
The unique complementarity of frame-based and event cameras for high frame rate object tracking has recently inspired some research attempts to develop multi-modal fusion approaches. However, these methods directly fuse both modalities and thus ignore the environmental attributes, e.g., motion blur, illumination variance, occlusion, scale variation, etc. Meanwhile, insufficient interaction between search and template features makes distinguishing target objects and backgrounds difficult. As a result, performance degradation is induced especially in challenging conditions. This paper proposes a novel and effective Transformer-based event-guided tracking framework, called eMoE-Tracker, which achieves new SOTA performance under various conditions. Our key idea is to disentangle the environment into several learnable attributes to dynamically learn the attribute-specific features and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsEnergy Efficient Wireless Sensor Networks · Air Quality Monitoring and Forecasting · Advanced Chemical Sensor Technologies
MethodsContrastive Learning
