Open AccessProbability‐based method for boosting human action recognition using scene context
Author(s) -
Zhang HongBo,
Lei Qing,
Chen DuanSheng,
Zhong BiNeng,
Peng Jialin,
Du JiXiang,
Su SongZhi
Publication year - 2016
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/iet-cvi.2015.0420
Subject(s) - action recognition , boosting (machine learning) , artificial intelligence , computer science , pattern recognition (psychology) , naive bayes classifier , action (physics) , context (archaeology) , context model , bayes' theorem , machine learning , computer vision , bayesian probability , support vector machine , object (grammar) , geography , physics , archaeology , quantum mechanics , class (philosophy)
In this study, the authors investigate the possibility of boosting action recognition performance by exploiting the associated scene context. Towards this end, the authors model a scene as a mid‐level ‘middle layer’ in order to bridge action descriptors and action categories. This is achieved via a scene topic model, in which hybrid visual descriptors, including spatial–temporal action features and scene descriptors, are first extracted from a video sequence. Then, the authors learn a joint probability distribution between scene and action using a naive Bayes nearest neighbour algorithm, which is adopted to jointly infer the action categories online by combining off‐the‐shelf action recognition algorithms. The authors demonstrate the advantages of their approach by comparing it with state‐of‐the‐art approaches using several action recognition benchmarks.