Learning Actionlet Ensemble for 3D Human Action Recognition

By Jiang Wang, Zicheng Liu, Ying Wu, Junsong Yuan. 2014

526 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

In 3D Vision & Pose

In Human-Computer Interaction

Citations in the corpus

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (2016, methodology): “[39], combined Fourier temporal pyramids of skeletal information with local occupancy pattern features extracted from depth maps and applied a data mining framework to discover the most discriminative combinations of body joints.”
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, methodology): “Among these approaches, the method in [26] uses the Fourier temporal pyramid [56] and the hand-crafted features for action classiﬁcation.”
A self-organizing neural network architecture for learning human-object interactions (2017, background): “Wang et al. [41] proposed a new 3D appearance feature called local occupancy pattern (LOP) describing the depth appearance in the neighborhood of a 3D joint, and thus capturing the relations between the human body parts, e.g. hands, and the environmental objects that the person is interacting with.”
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, methodology): “BOvW [58] and FV [43] or Fourier temporal pyramids in [73].”
RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, background): “The best result of the action recognition accuracy achieved on this dataset can only reach 85.75 % [98].”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “[121], [129] Actionlet Conc Lowlv Hand X X X”
Multimodal Multipart Learning for Action Recognition in Depth Videos (2015, methodology): “MSR-Action3D [5] is another depth based action dataset which provided depth sequences and skeleton information of 567 samples for 20 action classes.”
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.”
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.”
Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks (2017, neutral): “[48], [49] introduced an actionlet ensemble repre-”
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, neutral): “Skeleton-based action recognition has been explored in different aspects in recent years [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57].”
Learning and Refining of Privileged Information-Based RNNs for Action Recognition from Depth Sequences (2017, methodology): “Blanket: Similar to CAD60, we follow the protocol as [47] and perform cross-validation on our proposed dataset.”
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data (2017, methodology): “[40] use only the up-right pose frames in a sequence to determine the body plane by averaging the rotation transformation.”
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition (2016, methodology): “Human action recognition using 3D skeleton information is explored in diﬀerent aspects during recent years [33–50].”
A Review on Human Activity Recognition Using Vision-Based Method (2017, methodology): “Finally, as an extracted feature from depth maps itself, skeleton-based representation is often combined with original depth information to form more informative and robust representation [82, 83].”
Ieee Transactions on Pattern Analysis and Machine Inteligence 1 Super Normal Vector for Human Activity Recognition with Depth Cameras (unknown): “Wang et al. [40] [42] proposed the local and random occupancy patterns to describe depth appearances .”
Computer Vision and Image Understanding Computer Vision for Assistive Technologies (unknown): “…combining RGB and depth descriptors: they have been already successfully used to classify hand gestures for a human-machine interface application in the car ( Ohn-Bar and Trivedi, 2014 ) or to describe the articulated human body that has a large number of kinematic joints ( Wang et al., 2014a ).”
SSNet: Scale Selection Network for Online 3D Action Prediction (2018, methodology): “After the development of cheap and easy-to-use depth sensors, such as Kinect and XTion, human action recognition in 3D skeleton sequences becomes very popular [1, 79], and a series of hand-crafted features [72, 63, 75, 64, 52, 13, 70, 67] and deep learning based approaches [11, 83, 51, 30, 42, 26] h”