Global Context-Aware Attention LSTM Networks for 3D Action Recognition

By Jun Liu, G. Wang, Ping Hu, Ling-yu Duan, Alex ChiChung Kot. 2017

655 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition, Model Architectures

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

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Model Architectures

Citations in the corpus

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, methodology): “Previous works [30], [93] have shown that the importance degrees of the features from different body parts are not the same in analyzing different actions.”
Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, methodology): “Our SSNet also outperforms the Attention Net [85] that assigns weights to differen frames and joints.”
2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning (2018, methodology): “To cope with noisy skeletons, Spatio-Temporal LSTM networks have been widely used by applying a gating mechanism [26] to learn the reliability of skeleton sequences or by using attention mechanisms [27, 46].”
Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points (2018, neutral): “In [35], the ST-LSTM method of [34] is extended with a global context memory for skeleton-based action recognition.”
Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks (2017, background): “This work is an extension of our preliminary conference paper [31].”
Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, background): “However, using RNNs did not give an improvement over temporal pooling of convolutional features [82] or even over hand-crafted features.”
Joint Human Detection and Head Pose Estimation via Multistream Networks for RGB-D Videos (2017, methodology): “larly used in action classification [13]–[17], pose estimation [18], [19], and several methods are used for human detection.”
Human Action Recognition: Pose-Based Attention Draws Focus to Hands (2017, neutral): “2 GCA-LSTM [25] X - 74.”
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].”
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”
Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition (2017, background): “Skeleton-Based Action Recognition In recent years, skeleton-based action recognition problem attracts a lot of attention, and many learning-based methods [5, 24, 35, 21, 14, 13, 15] have been proposed.”
Recognizing Human Actions as the Evolution of Pose Estimation Maps (2018, methodology): “Recent deep learning models, e.g., CNN [17, 20], RNN [9] and LSTM [26, 25], have achieved high performances on the extracted 3D poses, which outperform methods [32, 50] that rely on raw depth video sequences.”
View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition (2018, methodology): “We compare our method with the deep learning based approaches that also leverage RNN or CNNwith skeleton data [6], [25], [27], [29], [30], [38], [42], and some traditional approaches using handcrafted features [7], [45].”
Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition (2021, neutral): “…89.9 4s MS-AAGCN (Shi et al. 2019b) 96.2 90.0 2s MS-G3D (Liu et al. 2020) 96.2 91.5 4s Shift-GCN (Cheng et (Ke et al. 2018) 62.2 61.8 SkeMotion (Liu et al. 2017) 67.7 66.9 TSRJI (Caetano et al. 2019) 67.9 62.8 4s Shift-GCN (Cheng et al. 2020) 85.9 87.6 2s MS-G3D (Liu et al. 2020) 86.9 88.4 Js…”
SS-LSTM: A Hierarchical LSTM Model for Pedestrian Trajectory Prediction (2018, background): “Recently, both RNN and LSTM have proved their successes in time sequence data processing areas such as speech recognition [7, 20], language translation [24], action recognition [30, 16] and image captioning [12, 4].”
An Empirical Study of Language CNN for Image Captioning (2016, methodology): “Models based on RNNs have dominated recent sequence modeling tasks [23, 31, 32, 44], and most of the recent image captioning models are based on LSTM networks [6, 19, 34].”
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.”