Hierarchical recurrent neural network for skeleton based action recognition

By Yong Du, Liang Wang. 2015

2,061 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: A Large Scale Dataset for 3D Human Activity Analysis (2016, methodology): “…13.61% HON4D [25] 30.56% 7.26% Lie Group [37] 50.08% 52.76% Skeletal Quads [10] 38.62% 41.36% FTP Dynamic Skeletons [15] 60.23% 65.22% HBRNN-L [9] 59.07% 63.97% This shows they have their model was prone to overﬁtting due to the lack of training data and proves the demand for a bigger dataset…”
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, background): “Recently, deep learning based-approaches have been proposed for 3D human activity analysis [9], [59], [60].”
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, methodology): “[9] applied a hierarchical RNN to discover common 3D action patterns in a data-driven learning method.”
Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks (2016, methodology): “With the proposed co-occurrence learning and in-depth dropout regularization, our full model also performs better than the manually designed hierarchical RNN approach.”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “, deep learning [22]) to process visual data at an acceptable speed.”
Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, background): “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.”
Video Representation Learning Using Discriminative Pooling (2018, background): “This problem may be tackled using recurrent models [1, 8, 9, 25, 45, 60], however such models are usually harder to train [32].”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “[26, 25] divided the whole skeleton sequence into five parts according to the human physical structure, and separately fed them into five bidirectional RNNs/LSTMs.”
When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition From Skeletal Data (2017, methodology): “If compared to [32, 21, 15, 5], the training time in this case is much longer even if using GPU acceleration.”
Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks (2017, methodology): “[12] introduced a hierarchical RNN model to represent the human body structure and temporal dynamics of the joints.”
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, methodology): “Both Co-occurrence LSTM [58] and Hierarchical RNN [37] adopt the Svaitzky-Golay filter in temporal domain to”
Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, methodology): “Compared with the pioneered hierarchical structure in [7], our structure is more succinct and straightforward, and does not use additional fully connected layers before the logistic regression classifier with softmax activation.”
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks (2017, background): “Hierarchical recurrent neural network of [6] combines the features of different body parts hierarchically.”
Pose-conditioned Spatio-Temporal Attention for Human Action Recognition (2017, methodology): “Similarly, Du et al [8] use bi-directional LSTM layers which fit anatomical hierarchy.”
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data (2017, methodology): “A general treatment employs a pre-processing step to transform the 3D joint coordinates from the camera coordinate system to a personcentric coordinate system by placing the body center at the origin, followed by rotating the skeleton such that the body plane is parallel to the (x, y)-plane, to make”
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding (2017, methodology): “In [11], a hierarchical RNN is utilized to model the temporal dynamics for skeleton based action recognition.”
A New Representation of Skeleton Sequences for 3D Action Recognition (2017, methodology): “For all datasets, the clips are generated with all frames of the original skeleton sequence without any pre-processing such as normalization, temporal down-sampling or noise ﬁl-tering.”