2018/05/29 by Thao Minh Le, Le, Thao Minh, Nakamasa Inoue +3
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Gait Recognition and Analysis #Hand Gesture Recognition Systems #Human Pose and Action Recognition
paper · pdf · doi:10.48550/arxiv.1805.11790
openalex publication_date 2018/05/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
This paper presents a new framework for human action recognition from a 3D skeleton sequence. Previous studies do not fully utilize the temporal relationships between video segments in a human action. Some studies successfully used very deep Convolutional Neural Network (CNN) models but often suffer from the data insufficiency problem. In this study, we first segment a skeleton sequence into distinct temporal segments in order to exploit the correlations between them. The temporal and spatial features of a skeleton sequence are then extracted simultaneously by utilizing a fine-to-coarse (F2C) CNN architecture optimized for human skeleton sequences. We evaluate our proposed method on NTU RGB+D and SBU Kinect Interaction dataset. It achieves 79.6% and 84.6% of accuracies on NTU RGB+D with cross-object and cross-view protocol, respectively, which are almost identical with the state-of-the-art performance. In addition, our method significantly improves the accuracy of the actions in two-person interactions.