activity
20142022
most citedDeep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences

36 citations · 73 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CV20222 cited

Contrastive Positive Mining for Unsupervised 3D Action Representation Learning

Haoyuan Zhang, Yonghong Hou, Wenjing Zhang +1

Recent contrastive based 3D action representation learning has made great progress. However, the strict positive/negative constraint is yet to be relaxed and the use of non-self po…

cs.CV20175 cited

Large-scale Isolated Gesture Recognition Using Convolutional Neural Networks

Pichao Wang, Wanqing Li, Song Liu +3

This paper proposes three simple, compact yet effective representations of depth sequences, referred to respectively as Dynamic Depth Images (DDI), Dynamic Depth Normal Images (DDN…

cs.CV20168 cited

Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks

Pichao Wang, Wanqing Li, Chuankun Li +1

Convolutional Neural Networks (ConvNets) have recently shown promising performance in many computer vision tasks, especially image-based recognition. How to effectively apply ConvN…

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.CV201611 cited

Large-scale Continuous Gesture Recognition Using Convolutional Neural Networks

Pichao Wang, Wanqing Li, Song Liu +3

This paper addresses the problem of continuous gesture recognition from sequences of depth maps using convolutional neutral networks (ConvNets). The proposed method first segments…

cs.CV201536 cited

Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences

Pichao Wang, Wanqing Li, Zhimin Gao +3

Recently, deep learning approach has achieved promising results in various fields of computer vision. In this paper, a new framework called Hierarchical Depth Motion Maps (HDMM) +…