View invariant human action recognition using histograms of 3D joints

By Lu Xia, Chia-Chih Chen, Jake K. Aggarwal. 2012

1,494 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, 3D Vision & Pose, Human-Computer Interaction

How researchers see this paper

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

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

In Human-Computer Interaction

Citations in the corpus

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, neutral): “UT-Kinect [15] 200 10 10 4 Kinect v1 RGB+D+3DJoints 2012”
Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks (2016, methodology): “The other is to explore temporal dependencies of the inter-frame content for action dynamics modeling, using hierarchical maximum entropy Markov model (Sung et al. 2011), hidden Markov model (Xia, Chen, and Aggarwal 2012) or Conditional Random Fields (Sminchisescu et al. 2005).”
RGB-D-based action recognition datasets: A survey (2016, neutral): “UTKinect UTKinect dataset [15] (http://cvrc.”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “Many other datasets captured using a Kinect v1 camera were also released to the public, including the MSR Daily Activity 3D [121], MSR Action Pairs [113], Online RGBD Action (ORGBD) [107], UTKinect-Action [124], Florence 3D-Action [118], CMU-MAD [104], UTD-MHAD [103], G3D/G3Di [105], [119], SPHERE [”
Multimodal Multipart Learning for Action Recognition in Depth Videos (2015, methodology): “In [7] spherical histograms of 3D locations of the joints went through HMM to model the temporal changes and final action classification.”
3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks (2014, neutral): “carefully designed features [36, 20, 35, 30].”
Histogram of Oriented Principal Components for Cross-View Action Recognition (2014, methodology): “Since HOPC and STK-Distribution capture complimentary information, their combination significantly improves classification accuracy which is over 22% higher than the nearest competitor on both datasets.”
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition (2014, methodology): “Experimental comparison on four datasets, including three benchmark ones [13,19,32], with eight state-of-the-art methods [4,10,19,21,31,32,35,36] shows the efficacy of our algorithms.”
Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, neutral): “research domain [26], [27], and a series of hand-crafted features [28], [29], [30], [31], [32], [33], [34], [35], [36], [37] and deep learning-based approaches [18], [19], [38], [39], [40], [41], [42], [43], [44] have been proposed.”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, neutral): “UTKinect UTKinect dataset [162](http://cvrc.”
When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition From Skeletal Data (2017, methodology): “In addition, we also compared with the reformulation of Histogramd of Oriented Gradients (HOG) features for joints [41] and the aggregation of local spatio-temporal features extracted from raw data [44].”
Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks (2017, methodology): “We evaluate our proposed method on the NTU RGB+D [52], UT-Kinect [44], SYSU-3D [68], SBU-Kinect Interaction [69], and Berkeley MHAD [70] datasets.”
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, methodology): “0% Histogram of 3D Joints [7] Geometric 90.”
Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, background): “, hidden Markov model [47, 49], to recognize actions.”
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data (2017, methodology): “Earlier works used hand-crafted features for action recognition from the skeleton [10, 45].”
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding (2017, neutral): “MSR-Action3D [17] 20 567 567 1 D+Skeleton No 2010 RGBD-HuDaAct [21] 13 1189 1189 1 RGB+D No 2011 MSR-DailyActivity [43] 16 320 320 1 RGB+D+Skeleton No 2012 Act4 [8] 14 6844 6844 1 RGB+D No 2012 UTKinect-Action [53] 10 200 200 1 RGB+D+Skeleton No 2012 3D Action Pairs [23] 12 360 360 1 RGB+D+Skeleton ”
A New Representation of Skeleton Sequences for 3D Action Recognition (2017, methodology): “With the prevalence of highly-accurate and affordable devices, action recognition based on 3D skeleton sequence has been attracting increasing attention [32, 28, 4, 24, 36, 16, 14].”
Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, methodology): “ction recognition have been proposed based on depth, RGB or skeleton data. These methods either extracted features from one modality: depth [65, 78, 42, 77, 37, 67, 68] or RGB [6, 40, 46] or skeleton [76, 75, 22, 13, 57, 72, 85, 8, 47], or fuse the features extracted separately from them at a later ”
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition (2016, methodology): “hallenges of this dataset include: (1) in most interactions, one person is acting and the other one is reacting; and (2) the joint coordinates in many sequences are of low accuracy. UT-Kinect Dataset [5]. This dataset contains 10 action classes performed by 10 subjects, captured with a stationary Ki”
A novel hierarchical framework for human action recognition (2016, methodology): “In previous works, it was used in two ways, either as one dataset containing all actions [7, 9–11, 14, 19–21] or by division into three subsets [6, 8, 12, 13, 15–19”