Roweisposes, Including Eigenposes, Supervised Eigenposes, and Fisherposes, for 3D Action Recognition
This work addresses the need for basic, non-deep learning methods in 3D action recognition, offering a generalized approach that includes variants like eigenposes and Fisherposes, but it is incremental as it adapts existing face recognition techniques to a new domain.
The paper tackles 3D action recognition by proposing Roweisposes, a family of methods based on generalized eigenvalue problems for discriminative subspace learning, and reports experimental verification on TST, UTKinect, and UCFKinect datasets.
Human action recognition is one of the important fields of computer vision and machine learning. Although various methods have been proposed for 3D action recognition, some of which are basic and some use deep learning, the need of basic methods based on generalized eigenvalue problem is sensed for action recognition. This need is especially sensed because of having similar basic methods in the field of face recognition such as eigenfaces and Fisherfaces. In this paper, we propose Roweisposes which uses Roweis discriminant analysis for generalized subspace learning. This method includes Fisherposes, eigenposes, supervised eigenposes, and double supervised eigenposes as its special cases. Roweisposes is a family of infinite number of action recongition methods which learn a discriminative subspace for embedding the body poses. Experiments on the TST, UTKinect, and UCFKinect datasets verify the effectiveness of the proposed method for action recognition.