Enhanced skeleton visualization for view invariant human action recognition

By Mengyuan Liu, Hong Liu. 2017

843 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. Liang Wang
3. G. Wang
4. Hanqing Lu
5. Yifan Zhang
6. Jian Cheng
7. Wanqing Li
8. Hossein Rahmani

In Computer Vision and Pattern Recognition

1. Jun Liu
2. G. Wang
3. Liang Wang
4. Luc Van Gool
5. Hossein Rahmani
6. Yi Yang
7. Ming-Hsuan Yang
8. Dacheng Tao

In Human-Computer Interaction

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

Citations in the corpus

• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, methodology): “The methods in [30], [47], [48], [94], [102], [105] all use RNN/LSTM for 3D action recognition, and the approaches in [49], [103], [104], [106], [107] all use convolutional networks for spatial and temporal modeling.”
• Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points (2018, neutral): “[36] P 86.”
• RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “The global encoding methods [53, 65, 83] would become less effective due to the repetition.”
• Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition (2019, methodology): “The earliest attempts of skeleton action recognition often encode all the body joint positions in each frame to a feature vector for pattern learning [27, 8, 6, 21].”
• Multi-Modal Domain Adaptation for Fine-Grained Action Recognition (2019, background): “of cross-viewpoint (or viewpoint-invariant) action recognition [24, 27, 31, 40, 46].”
• Fusing shape and motion matrices for view invariant action recognition using 3D skeletons (2017, background): “Based on depth and skeleton data, many works [8, 9, 10, 11, 12, 13] have been done to tackle with viewpoint variations.”
• An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition (2019, methodology): “Compared with the CNN-based method [17], our method also obtains much”
• Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN (2018, neutral): “CS CV Deep learning on Lie Group [15] 61.37% 66.95% JTM+CNN [49] 73.40% 75.20% Res-TCN [22] 74.30% 83.10% SkeletonNet(CNN) [20] 75.94% 81.16% JDM+CNN [31] 76.20% 82.30% Clips+CNN+MTLN [21] 79.57% 84.83% Enhanced Visualization+CNN [33] 80.03% 87.21% 1 Layer RNN [46] 56.02% 60.24% 2 Layer RNN [46] 56.”
• Skeleton-Based Action Recognition With Shift Graph Convolutional Network (2020, neutral): “…FLOPs (G) Lie Group [26] 52.8 50.1 - HBRNN [2] 64.0 59.1 - Deep-LSTM [19] 67.3 60.7 - VA-LSTM [35] 87.7 79.2 - TCN [7] 83.1 74.3 - Synthesized CNN [18] 87.2 80.0 - 3scale ResNet 152 [10] 90.9 84.6 - ST-GCN [34] 88.3 81.5 - Motif+VTDB [31] 90.2 84.2 - 2s AS-GCN [12] 94.2 86.8 27.0 2s Adaptive GCN…”
• Graph Distillation for Action Detection with Privileged Modalities (2017, background): “Specifically, with the availability of depth sensors and joint tracking algorithms, extensive research has been done on action classification and detection in RGB-D videos [39,47,48,61] as well as skeleton sequences [24,30,31,32,46,63].”
• 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] .”
• Multi-Modal Domain Adaptation for Fine-Grained Action Recognition (2020, background): “of cross-viewpoint (or viewpoint-invariant) action recognition [24, 27, 31, 40, 46].”
• Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition (2019, methodology): “, non-recurrent) convolutional neural networks for modeling sequences in speech, language [34, 10, 53, 48], and skeleton [18, 58, 30, 51] due to their superior performance.”
• Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning (2018, methodology): “These methods for skeleton-based action recognition can be divided into two categories: CNN-based methods [19, 31] and LSTM-based methods [32, 16, 26].”
• Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition (2018, methodology): “When increasing K 1 , K 2 , the local filtering region will cover (Vemulapalli, Arrate, and Chellappa 2014) 52.76% 50.08% Dynamic Skeletons (Hu et al. 2015) 65.22% 60.23% HBRNN (Du, Wang, and Wang 2015) 63.97% 59.07% LieNet (Huang et al. 2016) 66.95% 61.37% Deep LSTM (Shahroudy et al. 2016) 67.29% 60”
• InfoGCN: Representation Learning for Human Skeleton-based Action Recognition (2022, methodology): “In the early stages of deep learning-based approaches for skeleton-based action recognition, convolutional neural networks (CNNs) [10, 32, 46] and recurrent neural networks (RNNs) [11,25,31,53] were the standard models to adopt.”