Temporal Coherent and Graph Optimized Manifold Ranking for Visual Tracking

TL;DR

This paper introduces a novel unified ranking model for visual tracking that leverages temporal coherence and graph optimization to improve patch weighting by considering both spatial and temporal information.

Contribution

It proposes a new graph ranking approach that integrates spatial structure, unary patch features, and temporal correlations for enhanced visual tracking.

Findings

Improved tracking accuracy on benchmark datasets.

Effective utilization of temporal and structural information.

Enhanced discriminative power of patch weighting.

Abstract

Recently, weighted patch representation has been widely studied for alleviating the impact of background information included in bounding box to improve visual tracking results. However, existing weighted patch representation models generally exploit spatial structure information among patches in each frame separately which ignore (1) unary featureof each patch and (2) temporal correlation among patches in different frames. To address this problem, we propose a novel unified temporal coherence and graph optimized ranking model for weighted patch representation in visual tracking problem. There are three main contributions of this paper. First, we propose to employ a flexible graph ranking for patch weight computation which exploits both structure information among patches and unary feature of each patch simultaneously. Second, we propose a new more discriminative ranking model by further considering the temporal correlation among patches in different frames. Third, a neighborhood preserved, low-rank graph is learned and incorporated to build a unified optimized ranking model. Experiments on two benchmark datasets show the benefits of our model.