Hand gesture recognition with 3D convolutional neural networks

By Pavlo Molchanov, Shalini Gupta, Kihwan Kim, Jan Kautz. 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2015

495 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/99b26202f350c8d06eb3fcbf3226045b16c34eb5

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

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

A Survey on Deep Learning Based Approaches for Action and Gesture Recognition in Image Sequences (2017, background): “Similar in spirit, [63] introduces a 3D CNN for driver hand gesture recognition from depth and intensity data.”
Recurrent Convolutional Neural Networks for Continuous Sign Language Recognition by Staged Optimization (2017, background): “Recently, methods using deep convolutional neural networks (CNNs) have achieved breakthroughs in gesture recognition [20] and sign spotting [23, 30], and recurrent neural networks (RNNs) has shown significant results while learning the dynamic temporal dependencies in sign spotting [21, 26].”
A Low Power, Fully Event-Based Gesture Recognition System (2017, unknown): “Convolutional neural networks (CNNs) have been applied successfully to hand gesture recognition and localization [27, 32, 18, 40, 14], as have recurrent neural networks [28].”
A Unified Framework for Multi-Modal Isolated Gesture Recognition (2018, background): “…and etc. Continuous gesture recognition [Yin and Davis 2014; Evangelidis et al. 2014; Molchanov et al. 2016] and isolated gesture recognition [Molchanov et al. 2015; Wan et al. 2016; Wan et al. 2014] are the two main tasks of gesture recognition in computer vision and the former can be…”
Review of tool condition monitoring in machining and opportunities for deep learning (2020, methodology): “…owing to the max-pooling layers, the features acquired by the convolution layers The CNN method, which is frequently used in image recognition applications, is also used in gesture recognition [56 – 59], face recognition [60 – 62], scene labeling [63], and action recognition, as well [64, 65].”
Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks (2016, methodology): “Recent work using deep convolutional neural networks (CNN) with video sequences has significantly advanced the accuracy of dynamic hand gesture [22, 23, 25] and action [13, 34, 37] recognition.”
A review of hand gesture and sign language recognition techniques (2017, background): “[80] Molchanov et al 2015 3D Convolutional NN Depth threshold image gradient value Kinect 77.”
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects (2020, methodology): “NAG has been used to train CNN-based models in many tasks [89]–[91].”
MMTM: Multimodal Transfer Module for CNN Fusion (2019, background): “In [35], a novel 3D CNN is proposed to integrate depth and image gradient values to recognize dynamic hand gestures.”
Using Convolutional 3D Neural Networks for User-independent continuous gesture recognition (2016, methodology): “In a recent study, 3D Convolutional Neural Networks were proposed for the isolated hand gesture recognition task using depth and intensity modalities in automotive interfaces and reported a better recognition performance than using HOG descriptors [23].”
3D-based Deep Convolutional Neural Network for action recognition with depth sequences (2016, methodology): “Molchanov et al. [45] collected a gesture 165 data set and obtained 77.5% recognition accuracy using deep 3D Convolutional neural network.”
Multi-Modality Fusion based on Consensus-Voting and 3D Convolution for Isolated Gesture Recognition (2016, background): “Many methods have been proposed over the last few years [23, 14, 13, 36], which can be classified mainly into two categories: continuous gesture recognition and isolated gesture recognition.”
A Deep Neural Framework for Continuous Sign Language Recognition by Iterative Training (2019, background): “, human action recognition [18]–[20], gesture recognition [6] and sign spotting [9], [10], and recurrent neural networks (RNNs) have shown significant performance on learning the temporal dependencies in sign spotting [4], [21].”
Survey on Emotional Body Gesture Recognition (2018, background): “After the face, hands are probably the richest source of body language information [17], [18].”