Mining actionlet ensemble for action recognition with depth cameras
- Jiang Wang, Zicheng Liu, Ying Wu, Junsong Yuan
- Computer ScienceIEEE Conference on Computer Vision and Patternā¦
- 16 June 2012
An actionlet ensemble model is learnt to represent each action and to capture the intra-class variance, and novel features that are suitable for depth data are proposed.
Sparse reconstruction cost for abnormal event detection
- Yang Cong, Junsong Yuan, Ji Liu
- Computer ScienceComputer Vision and Pattern Recognition
- 20 June 2011
The method provides a unified solution to detect both local abnormal events and global abnormal events through a sparse reconstruction over the normal bases and extends it to support online abnormal event detection by updating the dictionary incrementally.
Learning Actionlet Ensemble for 3D Human Action Recognition
- Jiang Wang, Zicheng Liu, Ying Wu, Junsong Yuan
- Computer ScienceIEEE Transactions on Pattern Analysis and Machineā¦
- 1 May 2014
This paper proposes to characterize the human actions with a novel actionlet ensemble model, which represents the interaction of a subset of human joints, which is robust to noise, invariant to translational and temporal misalignment, and capable of characterizing both the human motion and the human-object interactions.
Robust Part-Based Hand Gesture Recognition Using Kinect Sensor
- Zhou Ren, Junsong Yuan, Jingjing Meng, Zhengyou Zhang
- Computer ScienceIEEE transactions on multimedia
- 1 August 2013
A novel distance metric, Finger-Earth Mover's Distance (FEMD), is proposed, which only matches the finger parts while not the whole hand, it can better distinguish the hand gestures of slight differences.
Robust hand gesture recognition based on finger-earth mover's distance with a commodity depth camera
- Zhou Ren, Junsong Yuan, Zhengyou Zhang
- Computer ScienceACM Multimedia
- 28 November 2011
A novel distance metric for hand dissimilarity measure, called Finger-Earth Mover's Distance (FEMD), which only matches fingers while not the whole hand shape, can better distinguish hand gestures of slight differences.
3D Hand Shape and Pose Estimation From a Single RGB Image
- Liuhao Ge, Zhou Ren, Junsong Yuan
- Computer ScienceComputer Vision and Pattern Recognition
- 3 March 2019
This work proposes a Graph Convolutional Neural Network (Graph CNN) based method to reconstruct a full 3D mesh of hand surface that contains richer information of both 3D hand shape and pose and proposes a weakly-supervised approach by leveraging the depth map as a weak supervision in training.
Fast action proposals for human action detection and search
- Gang Yu, Junsong Yuan
- Computer ScienceComputer Vision and Pattern Recognition
- 7 June 2015
Experimental results on two challenging datasets, MSRII and UCF 101, validate the superior performance of the action proposals as well as competitive results on action detection and search.
Towards Scalable Summarization of Consumer Videos Via Sparse Dictionary Selection
- Yang Cong, Junsong Yuan, Jiebo Luo
- Computer ScienceIEEE transactions on multimedia
- 1 February 2012
This work forms video summarization as a novel dictionary selection problem using sparsity consistency, where a dictionary of key frames is selected such that the original video can be best reconstructed from this representative dictionary.
3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation from Single Depth Images
- Liuhao Ge, Hui Liang, Junsong Yuan, D. Thalmann
- Computer ScienceComputer Vision and Pattern Recognition
- 21 July 2017
Experiments show that the proposed 3D CNN based approach outperforms state-of-the-art methods on two challenging hand pose datasets, and is very efficient as the implementation runs at over 215 fps on a standard computer with a single GPU.
Robust 3D Hand Pose Estimation in Single Depth Images: From Single-View CNN to Multi-View CNNs
- Liuhao Ge, Hui Liang, Junsong Yuan, D. Thalmann
- Computer ScienceComputer Vision and Pattern Recognition
- 23 June 2016
This work proposes to first project the query depth image onto three orthogonal planes and utilize these multi-view projections to regress for 2D heat-maps which estimate the joint positions on each plane to produce final 3D hand pose estimation with learned pose priors.
...
...