Prototype-based cross-modal object tracking

Lei Liu, Chenglong Li, Futian Wang, Longfeng Shen, Jin Tang

Abstract: Highlights•A prototype learning algorithm for cross-modal object tracking.•A multi-modal prototype to represent target information using multi-kind samples.•A prototype evaluation module to determine whether to perform prototype extraction based on the tracking result.•A prototype classification module to facilitate the dynamic prototype updating of the associated modality samples.