3 papers
physics.optics2018
Theoretical method for generating regular spatiotemporal pulsed-beam with controlled transverse-spatiotemporal dispersion
Zhaoyang Li, Noriaki Miyanaga
Herein we theoretically report a method that generates a transverse-spatiotemporal dispersion (T-STD), which is distinct from previous spatial, temporal, and longitudinal-spatiotem…
cs.CV2016
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks
Pichao Wang, Zhaoyang Li, Yonghong Hou +1
Recently, Convolutional Neural Networks (ConvNets) have shown promising performances in many computer vision tasks, especially image-based recognition. How to effectively use ConvN…
cs.CV2016
Combining ConvNets with Hand-Crafted Features for Action Recognition Based on an HMM-SVM Classifier
Pichao Wang, Zhaoyang Li, Yonghong Hou +1
This paper proposes a new framework for RGB-D-based action recognition that takes advantages of hand-designed features from skeleton data and deeply learned features from depth map…