Generalized symmetric pair model for action classification in still images

作者：

Highlights：

• A set of hypotheses based on observations on objects and actions.

• A Generalized Symmetric Pair Model (GSPM) as a type of region based model for action classification.

• An effective discriminative learning algorithm for GSPM.

摘要

•A set of hypotheses based on observations on objects and actions.•A Generalized Symmetric Pair Model (GSPM) as a type of region based model for action classification.•An effective discriminative learning algorithm for GSPM.

论文关键词：Generalized symmetry,Action classification,Semantically meaningful regions,Generalized symmetric pair model,Improved BoW framework

论文评审过程：Received 30 June 2015, Revised 30 May 2016, Accepted 2 October 2016, Available online 4 October 2016, Version of Record 4 December 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.10.001