Hand Gesture Recognition

41 papers with code • 18 benchmarks • 14 datasets

Hand gesture recognition (HGR) is a subarea of Computer Vision where the focus is on classifying a video or image containing a dynamic or static, respectively, hand gesture. In the static case, gestures are also generally called poses. HGR can also be performed with point cloud or joint hand data.

Benchmarks

Add a Result

These leaderboards are used to track progress in Hand Gesture Recognition

Dataset	Best Model	Compare
DHG-14	DD-Net	See all
DHG-28	DD-Net	See all
NVGesture	De+Recouple	See all
EgoGesture	ResNeXt-101	See all
SHREC 2017 track on 3D Hand Gesture Recognition	3DCNN_VIVA_4	See all
SHREC 2017	FPPR-PCD	See all
ChaLearn val	8-MFFs-3f1c (5 crop)	See all
VIVA Hand Gestures Dataset	MTUT	See all
LSA16	Prototypical Networks + CNN	See all
Jester test	DRX3D	See all
Cambridge	Key Frames + Feature Fusion	See all
RWTH-PHOENIX Handshapes dev set	DenseNet	See all
MGB	F-BLSTM	See all
BUAA	F-BGRU	See all
SmartWatch	F-BGRU	See all
Jester val	8-MFFs-3f1c (5 crop)	See all
ChaLean test	8-MFFs-3f1c	See all
Northwestern University	Key Frames + Feature Fusion	See all

Show all 18 benchmarks

Collapse benchmarks

Datasets

Most implemented papers

Most implemented Social Latest No code

Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks

ahmetgunduz/Real-time-GesRec • • 29 Jan 2019

We evaluate our architecture on two publicly available datasets - EgoGesture and NVIDIA Dynamic Hand Gesture Datasets - which require temporal detection and classification of the performed hand gestures.

Paper
Code

Make Skeleton-based Action Recognition Model Smaller, Faster and Better

fandulu/DD-Net • • arXiv 2019

Although skeleton-based action recognition has achieved great success in recent years, most of the existing methods may suffer from a large model size and slow execution speed.

Paper
Code

HGR-Net: A Fusion Network for Hand Gesture Segmentation and Recognition

Plrbear/HGR-Net • • 14 Jun 2018

We propose a two-stage convolutional neural network (CNN) architecture for robust recognition of hand gestures, called HGR-Net, where the first stage performs accurate semantic segmentation to determine hand regions, and the second stage identifies the gesture.

Paper
Code

Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison

dxli94/WLASL • • 24 Oct 2019

Based on this new large-scale dataset, we are able to experiment with several deep learning methods for word-level sign recognition and evaluate their performances in large scale scenarios.

Paper
Code

Human Computer Interaction Using Marker Based Hand Gesture Recognition

siam1251/HandGestureRecognition • 23 Jun 2016

Human Computer Interaction (HCI) has been redefined in this era.

Paper
Code

First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations

guiggh/hand_pose_action • CVPR 2018

Our dataset and experiments can be of interest to communities of 3D hand pose estimation, 6D object pose, and robotics as well as action recognition.

Paper
Code

Deep Fisher Discriminant Learning for Mobile Hand Gesture Recognition

chriswegmann/drone_steering • 12 Jul 2017

Gesture recognition is a challenging problem in the field of biometrics.

Paper
Code

A Study of Convolutional Architectures for Handshape Recognition applied to Sign Language

midusi/convolutional_handshape • • CACIC 2017

Using the LSA16 and RWTH-PHOENIX-Weather handshape datasets, we performed experiments with the LeNet, VGG16, ResNet-34 and All Convolutional architectures, as well as Inception with normal training and via transfer learning, and compared them to the state of the art in these datasets.

Paper
Code