A four-stream ConvNet based on spatial and depth flow for human action classification using RGB-D data
- 7 January 2020
- journal article
- research article
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 79 (17-18) , 11723-11746
Abstract
No abstract availableKeywords
This publication has 38 references indexed in Scilit:
- ReadingAct RGB-D action dataset and human action recognition from local featuresPattern Recognition Letters, 2014
- Human activity recognition from 3D data: A reviewPattern Recognition Letters, 2014
- Return of the Devil in the Details: Delving Deep into Convolutional Nets2014
- Spatio-temporal layout of human actions for improved bag-of-words action detectionPattern Recognition Letters, 2013
- RGB-D flow: Dense 3-D motion estimation using color and depth2013
- Human action recognition based on graph-embedded spatio-temporal subspacePattern Recognition, 2012
- Gradient-Enhanced Particle Filter for Vision-Based Motion Capture2007
- Regression-Based Human Motion Capture From Voxel Data2006
- Model-Based Human Motion Capture2005
- A Survey of Computer Vision-Based Human Motion CaptureComputer Vision and Image Understanding, 2001