Contextual saliency with an application to visual tracking

Matching local salient points is limited in some computer vision problems, since local features vary dramatically under large view changes. In a selective attention tracking paradigm, this paper proposes a new definition on salient points which includes context information around the given point. The proposed contextual salient points are extracted based on the geometry structure of the manifold embedded in the image feature space. Extensive experiments show that such contextual saliency leads to superior performances in many challenging target tracking tasks.