2020/11/11 by Negar Heidari, Heidari, Negar, Alexandros Iosifidis +1 · 1 citation
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #Context-Aware Activity Recognition Systems #FOS: Computer and information sciences #Human Pose and Action Recognition #Machine Learning (cs.LG) #Stroke Rehabilitation and Recovery #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2011.05668
Accepted by the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021)
openalex publication_date 2020/11/11 · arxiv created 2021/04/26 · arxiv updated 2021/04/28 · openalex created_date 2022/07/25 · openalex updated_date 2026/08/04
Graph convolutional networks (GCNs) have been very successful in skeleton-based human action recognition where the sequence of skeletons is modeled as a graph. However, most of the GCN-based methods in this area train a deep feed-forward network with a fixed topology that leads to high computational complexity and restricts their application in low computation scenarios. In this paper, we propose a method to automatically find a compact and problem-specific topology for spatio-temporal graph convolutional networks in a progressive manner. Experimental results on two widely used datasets for skeleton-based human action recognition indicate that the proposed method has competitive or even better classification performance compared to the state-of-the-art methods with much lower computational complexity.