Effective 3D action recognition using EigenJoints

By Xiaodong Yang, Yingli Tian. 2014

366 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks (2016, background): “One is to design robust and discriminative features from the skeleton (and the corresponding RGBD images) for intra-frame content representation (M ¨ uller, R ¨ oder, and Clausen 2005; Wang, Liu, and Junsong 2012; Sung et al. 2012; Yang and Tian 2014; Ji, Ye, and Cheng 2014).”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “For example, the traditional PCA method is applied for dimension reduction to extract low-dimensional features from raw skeleton features [130], [131], [209].”
Multimodal Multipart Learning for Action Recognition in Depth Videos (2015, methodology): “…Action Subsets of [5] Method (protocol of [5]) Accuracy Action Graph on Bag of 3D Points [5] 74.7% Histogram of 3D Joints [7] 79.0% EigenJoints [6] 83.3% Random Occupancy Patterns [8] 86.5% Depth HOG [38] 91.6% Lie Group [39] 92.5% JAS+HOG 2 [40] 94.8% DL-GSGC+TPM [41] 96.7% Proposed MMMP…”
Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, methodology): “With the advent of cheap and easy-to-use depth sensors, such as Kinect [8], 3D skeleton-based human action recognition became a popular research domain [26, 27], and a series of hand-crafted features [28–37] and deep learning-based approaches [18, 19, 38–44] have been proposed.”
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition (2016, methodology): “For example, Yang and Tian [4] represented the static postures and the dynamics of the motion patterns via eigenjoints and utilized a Na¨ıve-Bayes-Nearest-Neighbor classiﬁer learning.”
Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons (2016, methodology): “In [18], the relative joint positions and their temporal displacements are modeled with respect to the initial frame.”
Evaluating spatiotemporal interest point features for depth-based action recognition (2014, methodology): “Different from [16] where the Naive Bayes classifier was used, we compute the histogram of the joints to combinewith the STIP features by the random forests method.”
Learning hierarchical spatio-temporal pattern for human activity prediction (2016, methodology): “Method Same-environment Cross-environment Moving Pose [36] 38.4 28.5 Eigenjoints [35] 49.1 35.7 Proposed method 49.5 50.9 throw, push, pull, wave hands, and clap hands.”
Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition (2017, methodology): “[31] use NBNN to classify 3D actions represented by dimension-reduced action descriptors, EigenJoint.”
Low-Rank Tensor Subspace Learning for RGB-D Action Recognition (2016, background): “• Yang and Tian [41] extracted Accumulated Motion Energy from different views of action videos and jointed them together.”
Activity Recognition for Natural Human Robot Interaction (2014, neutral): “50 Yang, Tian[15] 71.”
Ieee Transactions on Pattern Analysis and Machine Inteligence 1 Super Normal Vector for Human Activity Recognition with Depth Cameras (neutral): “A number of representations of human activity in depth sequences have been explored, ranging from skeleton joints [36] [50], cloud points [40] [42], projected depth maps [20] [49], local interest points [10], [47] to surface normals [27] [51].”
Hidden Markov Model on a unit hypersphere space for gesture trajectory recognition (2014, methodology): “, sign language recognition (Han et al., 2009; Kong and Ranganath, 2010), and human action recognition (Rao et al., 2002; Ellis et al., 2013; Yang and Tian, 2013; Xia et al., 2012).”
A Comprehensive Survey of Vision-Based Human Action Recognition Methods (2019, methodology): “on depth information [14–16], and action features based on human pose changes [17,18].”