Multi-layer representation for cross-view action recognition

Abstract

Daily action recognition is an important application domain in computer vision. Considering the complex temporal structure and view changes of daily actions, we propose a multi-layer representation for cross-view action recognition (MRCAR) based on two-stage optimization using a training set and a validation set. In the first stage, a cross-view atomic dictionary learning model is constructed based on jointly sparse constraints, utilizing the original features of the training set. Subsequently, a shared atomic dictionary, containing representative view-independent information, is obtained through alternating optimization. In the second stage, a reconstruction function based on the obtained shared atomic dictionary is developed. This function is employed to acquire sparse codes for the training and validation sets, enhancing the representativeness of motion atoms and improving overall recognition performance. Finally, experimental results from the WVU (West Virginia University) dataset and the NTU (Nanyang Technological University) RGB-D 120 dataset demonstrate that the proposed MRCAR method achieves an accuracy improvement of 3%-20% over recent state-of-the-art methods.