Adaptive multi-view graph convolutional networks for skeleton-based action recognition
Authors:
- Xing LiuXLXing Liu
- Yanshan LiYLYanshan Li
- Rongjie XiaRXRongjie Xia
- 1 July 2021
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 444, 288-300
Abstract
No abstract availableKeywords
Funding Information
- Natural Science Foundation of Guangdong Province (2017A030313343, 2019A1515011307, 61771319, 61871154, JCYJ20180507182259896)
- National Natural Science Foundation of China (2017A030313343, 2019A1515011307, 61771319, 61871154, JCYJ20180507182259896)
- Science and Technology Planning Project of Shenzen Municipality (2017A030313343, 2019A1515011307, 61771319, 61871154, JCYJ20180507182259896)
This publication has 34 references indexed in Scilit:
- Combining depth-skeleton feature with sparse coding for action recognitionNeurocomputing, 2017
- Skeleton Optical Spectra-Based Action Recognition Using Convolutional Neural NetworksIEEE Transactions on Circuits and Systems for Video Technology, 2016
- Spatiotemporal representation of 3D skeleton joints-based action recognition using modified spherical harmonicsPattern Recognition Letters, 2016
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis2016
- From action to activity: Sensor-based activity recognitionNeurocomputing, 2016
- Effective Active Skeleton Representation for Low Latency Human Action RecognitionIEEE Transactions on Multimedia, 2015
- Cross-View Action Modeling, Learning, and Recognition2014
- Manifold-constrained coding and sparse representation for human action recognitionPattern Recognition, 2013
- Real-time human pose recognition in parts from single depth imagesCommunications of the ACM, 2013
- View invariant human action recognition using histograms of 3D joints2012