Skeleton based action recognition with convolutional neural network

By Yong Du, Yun Raymond Fu, Liang Wang. 2015

436 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, 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

1. Jun Liu
2. Hanqing Lu
3. Yifan Zhang
4. Jian Cheng
5. Liang Wang
6. Wanqing Li
7. G. Wang
8. Pichao Wang

In Computer Vision and Pattern Recognition

1. Jun Liu
2. G. Wang
3. Liang Wang
4. Wanqing Li
5. Pichao Wang
6. Hanqing Lu
7. Jian Cheng
8. Yifan Zhang

In Human-Computer Interaction

1. Yifan Zhang
2. Hanqing Lu
3. Jian Cheng
4. Pichao Wang
5. Wanqing Li
6. Jun Liu
7. Liang Wang
8. Philip O. Ogunbona

Citations in the corpus

• Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, neutral): “Most of the existing skeleton-based action recognition methods [30], [40], [45], [46], [47], [48] receive the fully observed segmented videos as input (each sample contains”
• RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, background): “Most of available datasets require subjects to perform actions in a visible and restricted view to avoid occlusion, and this results in limited view data collection and less 29 SBU Kinect Interaction [149] Depth+ Skeleton PRNN Side Information 89.20% [130] Skeleton Co-occurrence +LSTM None 90.41% [1”
• Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, neutral): “Precision Recall F1-score Skeleton Feature [48] 59.9 59.3 59.6 Portfolios [52] – – 56.0 Gesture Spotting [35] 61.2 62.3 61.7 HiVideoDarwin [45] 74.9 75.6 74.6 CNN for Skeleton [5] 91”
• Skeleton-Based Action Recognition With Directed Graph Neural Networks (2019, methodology): “Another framework, involving the image-based methods, represents the skeleton data as a pseudo-image to implement CNNs applied successfully in the field of image classification [6, 14, 21, 16] .”
• Human Action Recognition From Various Data Modalities: A Review (2020, neutral): “[186] 2015 - - - Hou et al.”
• A Real-Time and Hardware-Efficient Processor for Skeleton-Based Action Recognition With Lightweight Convolutional Neural Network (2019, background): “At the same time, many works [10], [11] flatten the dynamic skeleton into 2D matrices arranged by spatial and temporal order in order to feed a two-dimensional convolutional neural network.”
• 3D action recognition using data visualization and convolutional neural networks (2017, methodology): “In [13], a skeleton sequence is arranged as a color image, which mainly captures the temporal evolutions of skeleton joints.”
• Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN (2017, methodology): “[22] Fig.”
• Skeleton boxes: Solving skeleton based action detection with a single deep convolutional neural network (2017, methodology): “Similar to the work in [10], we divide all human skeleton joints in each frame into five main parts according to human physical structure, i.e . two arms, two legs and a trunk.”
• SSNet: Scale Selection Network for Online 3D Action Prediction (2018, background): “Most of the existing 3D action recognition methods [63, 51, 57, 69, 24, 66, 10, 29] take fully observed segmented videos as input (each sample contains one full action instance), and output a class label.”
• Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition (2019, background): “Previous CNN-based works [18, 6, 58], however, typically overlook the semantics by implicitly hiding them in the 2D skeleton map (e.”
• An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition (2019, background): “The Convolutional Neural Networks (CNNs) are used to learn spatial-temporal features from skeletons in [4, 14, 10].”
• Enhanced skeleton visualization for view invariant human action recognition (2017, methodology): “6 also compares our method with [20] and [21] , which can be considered as two specific cases of our visualization method.”
• View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition (2018, methodology): “the range of 0-255 is performed based on dataset statistics [4] or sequence statistics [23].”
• Joint Distance Maps Based Action Recognition With Convolutional Neural Networks (2017, methodology): “The proposed method follows a similar approach to that in the works [20], [21].”