A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition
This work addresses the problem of insufficient temporal modeling in skeleton-based action recognition for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles 3D human action recognition by proposing a fine-to-coarse CNN framework that segments skeleton sequences to exploit temporal correlations, achieving accuracies of 79.6% and 84.6% on NTU RGB+D datasets and improving performance for two-person interactions.
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.