3D skeleton-based human action classification: A survey

By Liliana Lo Presti, Marco La Cascia. 2016

414 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

1. Jun Liu
2. G. Wang
3. Alex ChiChung Kot
4. Ling-yu Duan
5. Amir Shahroudy
6. Wanqing Li
7. Pichao Wang
8. Qiuhong Ke

In Computer Vision and Pattern Recognition

1. Jun Liu
2. G. Wang
3. Hossein Rahmani
4. Alex ChiChung Kot
5. Amir Shahroudy
6. Wanqing Li
7. Ling-yu Duan
8. Pichao Wang

In 3D Vision & Pose

1. Jun Liu
2. Amir Shahroudy
3. G. Wang
4. Pichao Wang
5. Alex ChiChung Kot
6. Fatih Murat Porikli
7. Ling-yu Duan
8. Yonghong Hou

In Human-Computer Interaction

1. Jun Liu
2. Pichao Wang
3. Wanqing Li
4. G. Wang
5. Yonghong Hou
6. Amir Shahroudy
7. Hossein Rahmani
8. Chuankun Li

Citations in the corpus

• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, background): “Readers are referred to these survey papers [31], [32], [33], [34], [35], [36] for a more extensive list of the current 3D activity analysis datasets and methods.”
• Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, background): “In recent years, human activity analysis based on human skeletal data has attracted a lot of attention, and various methods for feature extraction and classifier learning have been developed for skeleton-based action recognition [1], [2], [3].”
• View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data (2017, background): “…studied over the past few decades, 3D skeleton based human representa-∗ tion for action recognition has recently attracted a lot of research attention because of its high level representation and robustness to variations of viewpoints, appearances, and surrounding distractions [2, 10, 28, 47].”
• Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons (2016, background): “Keywords: Kernel descriptors, skeleton action recognition, higher-order tensors”
• A Comprehensive Survey of Vision-Based Human Action Recognition Methods (2019, neutral): “Human action recognition has a wide range of applications, such as intelligent video surveillance and environmental home monitoring [1,2], video storage and retrieval [3,4], intelligent human–machine interfaces [5,6], and identity recognition [7].”
• SSNet: Scale Selection Network for Online 3D Action Prediction (2018, background): “As a result, activity analysis with 3D skeleton data becomes popular [19, 49, 62, 41, 81, 57, 43] due to its succinctness, high level representation, and robustness against variations in viewpoints, clothing textures, illumination, and background [11, 42, 23].”
• A Real-Time and Hardware-Efficient Processor for Skeleton-Based Action Recognition With Lightweight Convolutional Neural Network (2019, methodology): “At 400MHz, the processor could make inference for 4 actions per second which is real-time [21], [22] for HAR.”
• Global Context-Aware Attention LSTM Networks for 3D Action Recognition (2017, methodology): “With the advent of depth sensors, such as Microsoft Kinect, Asus Xtion, and Intel RealSense, action recognition using 3D skeleton sequences has attracted a lot of research attention, and lots of advanced approaches have been proposed [33, 14, 1, 72].”