Describe and Attend to Track: Learning Natural Language guided Structural Representation and Visual Attention for Object Tracking

TL;DR

This paper introduces a structure-aware deep neural network for object tracking that leverages graph-based relationships among samples and integrates natural language cues to improve robustness and re-identification, especially under occlusion.

Contribution

It proposes a novel graph-based neural network that incorporates natural language guidance and visual attention mechanisms for enhanced object tracking.

Findings

Effective in handling occlusion and out-of-view scenarios

Outperforms existing methods on five benchmark datasets

Integrates natural language cues into visual tracking

Abstract

The tracking-by-detection framework requires a set of positive and negative training samples to learn robust tracking models for precise localization of target objects. However, existing tracking models mostly treat different samples independently while ignores the relationship information among them. In this paper, we propose a novel structure-aware deep neural network to overcome such limitations. In particular, we construct a graph to represent the pairwise relationships among training samples, and additionally take the natural language as the supervised information to learn both feature representations and classifiers robustly. To refine the states of the target and re-track the target when it is back to view from heavy occlusion and out of view, we elaborately design a novel subnetwork to learn the target-driven visual attentions from the guidance of both visual and natural language cues. Extensive experiments on five tracking benchmark datasets validated the effectiveness of our proposed method.