DeepGRU: Deep Gesture Recognition Utility

@inproceedings{Maghoumi2019DeepGRUDG,
  title={DeepGRU: Deep Gesture Recognition Utility},
  author={Mehran Maghoumi and Joseph J. LaViola},
  booktitle={ISVC},
  year={2019}
}
We propose DeepGRU, a novel end-to-end deep network model informed by recent developments in deep learning for gesture and action recognition, that is streamlined and device-agnostic. [...] Key Method At the heart of our method lies a set of stacked gated recurrent units (GRU), two fully-connected layers and a novel global attention model. We evaluate our method on seven publicly available datasets, containing various number of samples and spanning over a broad range of interactions (full-body, multi-actor…Expand
Classifying In-Place Gestures with End-to-End Point Cloud Learning
TLDR
An end-to-end joint framework involving both a supervised loss for supervised point learning and an unsupervised loss for un supervised domain adaptation for accurate and efficient classification of in-place gestures is proposed.
Air-Writing Recognition using Deep Convolutional and Recurrent Neural Network Architectures
In this paper, we explore deep learning architectures applied to the air-writing recognition problem where a person writes text freely in the three dimensional space. We focus on handwritten digits,
DeepNAG: Deep Non-Adversarial Gesture Generation
TLDR
A novel, device-agnostic GAN model for gesture synthesis called DeepGAN is discussed and a new differentiable loss function based on dynamic time warping and the average Hausdorff distance is introduced, which allows DeepGAN’s generator to be trained without requiring a discriminator.
Fusion of 2D CNN and 3D DenseNet for Dynamic Gesture Recognition
TLDR
An effective dynamic gesture recognition method is proposed by fusing the prediction results of a two-dimensional motion representation convolution neural network (CNN) model and three-dimensional dense convolutional network (DenseNet) model.
Recognizing Skeleton-Based Hand Gestures by a Spatio-Temporal Network
  • Xin Li
  • 2021
A key challenge in skeleton-based hand gesture recognition is the fact that a gesture can often be performed in several different ways, with each consisting of its own configuration of poses and
Efficient Multi-stream Temporal Learning and Post-fusion Strategy for 3D Skeleton-based Hand Activity Recognition
TLDR
This paper proposes a new hybrid learning pipeline for skeleton-based hand activity recognition, which is composed of three blocks, and shows that this approach performs better than the state-of-the-art approaches.
MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition
Convolutional neural networks are nowadays witnessing a major success in different pattern recognition problems. These learning models were basically designed to handle vectorial data such as images
Skeleton-Based Dynamic Hand Gesture Recognition Using a Part-Based GRU-RNN for Gesture-Based Interface
TLDR
A skeleton-based dynamic hand gesture recognition method that divides geometric features into multiple parts and uses a gated recurrent unit-recurrent neural network (GRU-RNN) for each feature part.
GestureVLAD: Combining Unsupervised Features Representation and Spatio-Temporal Aggregation for Doppler-Radar Gesture Recognition
TLDR
A shallow learning approach for gesture recognition, that is based on unsupervised range-Doppler features representation, along with a learnable pooling aggregation via NetVLAD, which outperforms state-of-the-art approaches in terms of recognition accuracy and speed for sequence-level hand gesture classification.
Compact joints encoding for skeleton-based dynamic hand gesture recognition
TLDR
A novel framework for skeleton-based dynamic hand gesture recognition and a compact joints encoding method that can adaptively select compact joints based on the convex hull of the hand skeleton and encode them into a skeleton image for fully extracting spatial features are proposed.
...
1
2
3
4
...

References

SHOWING 1-10 OF 78 REFERENCES
Deep Learning for Hand Gesture Recognition on Skeletal Data
TLDR
A new Convolutional Neural Network (CNN) where sequences of hand-skeletal joints' positions are processed by parallel convolutions is proposed where this model achieves a state-of-the-art performance on a challenging dataset.
Convolutional Neural Networks and Long Short-Term Memory for skeleton-based human activity and hand gesture recognition
TLDR
A deep learning-based approach for temporal 3D pose recognition problems based on a combination of a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) recurrent network and a data augmentation method that has also been validated experimentally is proposed.
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
TLDR
A large-scale dataset for RGB+D human action recognition with more than 56 thousand video samples and 4 million frames, collected from 40 distinct subjects is introduced and a new recurrent neural network structure is proposed to model the long-term temporal correlation of the features for each body part, and utilize them for better action classification.
SkeletonNet: Mining Deep Part Features for 3-D Action Recognition
TLDR
This letter presents SkeletonNet, a deep learning framework for skeleton-based 3-D action recognition, which contains two parts: one to extract general features from the input images, while the other to generate a discriminative and compact representation for action recognition.
CNN-based Action Recognition and Supervised Domain Adaptation on 3D Body Skeletons via Kernel Feature Maps
TLDR
A new representation is proposed which encodes sequences of 3D body skeleton joints in texture-like representations derived from mathematically rigorous kernel methods which lets us leverage the available Kinect-based data beyond training on a single dataset and outperform simple fine-tuning on any two datasets combined in a naive manner.
Beyond Joints: Learning Representations From Primitive Geometries for Skeleton-Based Action Recognition and Detection
TLDR
This work aims to leverage the geometric relations among joints for action recognition by introducing three primitive geometries: joints, edges, and surfaces and dramatically outperforms the existing state-of-the-art methods for both tasks of action recognition and action detection.
Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition
TLDR
A deep progressive reinforcement learning (DPRL) method for action recognition in skeleton-based videos, which aims to distil the most informative frames and discard ambiguous frames in sequences for recognizing actions.
Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks
TLDR
A compact, effective yet simple method to encode spatio-temporal information carried in 3D skeleton sequences into multiple 2D images, referred to as Joint Trajectory Maps (JTM), and ConvNets are adopted to exploit the discriminative features for real-time human action recognition.
Human Action Recognition: Pose-Based Attention Draws Focus to Hands
TLDR
An extensive ablation study is performed to show the strengths of this approach and the conditioning aspect of the attention mechanism and to evaluate the method on the largest currently available human action recognition dataset, NTU-RGB+D, and report state-of-the-art results.
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
TLDR
This work proposes an end-to-end spatial and temporal attention model for human action recognition from skeleton data on top of the Recurrent Neural Networks with Long Short-Term Memory (LSTM), which learns to selectively focus on discriminative joints of skeleton within each frame of the inputs and pays different levels of attention to the outputs of different frames.
...
1
2
3
4
5
...