Robust visual tracking via efficient manifold ranking with low-dimensional compressive features
作者：
Highlights：
• A novel graph-manifold ranking based visual tracking method is proposed.
• An efficient manifold ranking method is adopted to reconstruct graph efficiently.
• Low-dimensional compressive features are used for object representation.
• Our method exploits temporal and spatial context information.
• The proposed method outperforms the reference trackers on challenging datasets.
摘要
Highlights•A novel graph-manifold ranking based visual tracking method is proposed.•An efficient manifold ranking method is adopted to reconstruct graph efficiently.•Low-dimensional compressive features are used for object representation.•Our method exploits temporal and spatial context information.•The proposed method outperforms the reference trackers on challenging datasets.
论文关键词：Visual tracking,Appearance model,Manifold ranking,Random projections,Low-dimensional compressive features,Spatial context
论文评审过程：Received 20 April 2014, Revised 26 December 2014, Accepted 9 March 2015, Available online 19 March 2015.
论文官网地址：https://doi.org/10.1016/j.patcog.2015.03.008
