Learning Occlusion-Dynamic Invariant Representations for Multi-Object Tracking.

Abstract

Robust multi-object tracking (MOT) is hindered by the instability of appearance features under visual corruptions such as occlusion and motion blur. These perturbations introduce high-variance noise into feature trajectories, weakening temporal representations and causing identity switches. We address this challenge by learning more stable appearance representations under feature corruption. To this end, we propose the Causal Interaction Module (CIM), a causal architecture that follows a filter then reconstruct design for online tracking. A temporal filtering stage summarizes the historical feature trajectory into a stable anchor, and a contextual enhancement stage uses that anchor to refine frame-level features before association. Integrated into standard trackers, CIM improves association robustness while preserving the host tracking formulation. Experiments on multiple MOT benchmarks and corruption stress tests show consistent gains, especially on association-related metrics.