Several recent reviews of content

Specific CBVRs for retrieving video shots from a query with human actions have been described by Jones and Shao (2013) and in Laptev, Marszalek, Schmid, and Rozenfeld (2008) by using a full movie repository. A large scale data mining methods that Wortmannin uses unsupervised clustering of human action videos was described by Liao, Liu, Xiao, and Liu (2013). Another study, that could treat more than 100 human actions, has been reported by Nga and Yanai (2014).