Reading Relevant Feature from Global Representation Memory for Visual Object Tracking

TL;DR

This paper introduces a novel visual object tracking method that uses relevance attention and a global memory to dynamically select and utilize the most relevant historical features, improving tracking efficiency and accuracy.

Contribution

It proposes a relevance attention mechanism combined with a global memory that adaptively selects pertinent historical features for each frame, reducing redundancy and enhancing tracking performance.

Findings

Achieves competitive results on five challenging datasets.

Operates at 71 FPS, demonstrating real-time capability.

Effectively reduces redundancy by selecting relevant historical features.

Abstract

Reference features from a template or historical frames are crucial for visual object tracking. Prior works utilize all features from a fixed template or memory for visual object tracking. However, due to the dynamic nature of videos, the required reference historical information for different search regions at different time steps is also inconsistent. Therefore, using all features in the template and memory can lead to redundancy and impair tracking performance. To alleviate this issue, we propose a novel tracking paradigm, consisting of a relevance attention mechanism and a global representation memory, which can adaptively assist the search region in selecting the most relevant historical information from reference features. Specifically, the proposed relevance attention mechanism in this work differs from previous approaches in that it can dynamically choose and build the optimal global representation memory for the current frame by accessing cross-frame information globally. Moreover, it can flexibly read the relevant historical information from the constructed memory to reduce redundancy and counteract the negative effects of harmful information. Extensive experiments validate the effectiveness of the proposed method, achieving competitive performance on five challenging datasets with 71 FPS.