Human activity recognition in videos using a single example

作者：

Highlights：

• A hierarchical structure for accurate video to video matching and event recognition

• Incorporating contextual information to the “bag of video words” framework

• Coding spatio-temporal compositions of video volumes by a probabilistic framework

摘要

•A hierarchical structure for accurate video to video matching and event recognition•Incorporating contextual information to the “bag of video words” framework•Coding spatio-temporal compositions of video volumes by a probabilistic framework

论文关键词：Action recognition,Bag of video words,Hierarchical codebook,Spatio-temporal contextual information,Probabilistic modeling,Context,Ensemble of volumes

论文评审过程：Received 25 January 2013, Revised 18 July 2013, Accepted 29 August 2013, Available online 6 September 2013.

论文官网地址：https://doi.org/10.1016/j.imavis.2013.08.005