Learning Progressive Adaptation for Multi-Modal Tracking (PATrack)

We propose to perform Progressive Adaptation for Multi-Modal Tracking (PATrack). Our design integrates intra-modal, inter-modal, and task-level adapters into a unified framework. Extensive experiments on RGB+Thermal, RGB+Depth, and RGB+Event tracking tasks demonstrate that our method shows impressive performance.

Pipeline

Resuts on LasHeR, VisEvent, and DepthTrack

Resuts on GTOT and RGBT234