Informative joints based human action recognition using skeleton contexts
作者：
Highlights：
• Our informative joints based method eliminates noise by ignoring the joints of small contributions.
• We use binned pairwise space distribution of informative joints to build discriminative skeleton contexts.
• Our representation is strongly invariant to individual size and shape, and viewpoint.
• Improved affinity propagation was used to automatically find the exemplar features without worrying about bad initialization.
• The proposed approach is discriminative for similar human action recognition and well adapted to the intra-class variation.
摘要
Highlights•Our informative joints based method eliminates noise by ignoring the joints of small contributions.•We use binned pairwise space distribution of informative joints to build discriminative skeleton contexts.•Our representation is strongly invariant to individual size and shape, and viewpoint.•Improved affinity propagation was used to automatically find the exemplar features without worrying about bad initialization.•The proposed approach is discriminative for similar human action recognition and well adapted to the intra-class variation.
论文关键词：Action recognition,Skeleton contexts,Informative joints,Affinity propagation,CRFs,Kinect
论文评审过程：Received 15 August 2014, Revised 7 February 2015, Accepted 10 February 2015, Available online 18 February 2015.
论文官网地址：https://doi.org/10.1016/j.image.2015.02.004
