TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Hand Gesture Recognition	DHG-14	Parallel-Conv	Accuracy	91.28	# 5
Hand Gesture Recognition	DHG-28	Parallel-Conv	Accuracy	84.35	# 5

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/deep-learning-for-hand-gesture-recognition-on/hand-gesture-recognition-on-dhg-14)](https://paperswithcode.com/sota/hand-gesture-recognition-on-dhg-14?p=deep-learning-for-hand-gesture-recognition-on)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/deep-learning-for-hand-gesture-recognition-on/hand-gesture-recognition-on-dhg-28)](https://paperswithcode.com/sota/hand-gesture-recognition-on-dhg-28?p=deep-learning-for-hand-gesture-recognition-on)`

Deep Learning for Hand Gesture Recognition on Skeletal Data

IEEE FG 2018 2018 · Guillaume Devineau, Wang Xi, Jie Yang, Fabien Moutarde ·

In this paper, we introduce a new 3D hand gesture recognition approach based on a deep learning model. We introduce a new Convolutional Neural Network (CNN) where sequences of hand-skeletal joints’ positions are processed by parallel convolutions; we then investigate the performance of this model on hand gesture sequence classification tasks. Our model only uses hand-skeletal data and no depth image. Experimental results show that our approach achieves a state-of-the-art performance on a challenging dataset (DHG dataset from the SHREC 2017 3D Shape Retrieval Contest), when compared to other published approaches. Our model achieves a 91.28% classification accuracy for the 14 gesture classes case and an 84.35% classification accuracy for the 28 gesture classes case.

PDF