3,505 Hits in 8.4 sec

HAN: An Efficient Hierarchical Self-Attention Network for Skeleton-Based Gesture Recognition [article]

Jianbo Liu, Ying Wang, Shiming Xiang, Chunhong Pan
2021 arXiv   pre-print
Previous methods for skeleton-based gesture recognition mostly arrange the skeleton sequence into a pseudo picture or spatial-temporal graph and apply deep Convolutional Neural Network (CNN) or Graph Convolutional  ...  In terms of temporal features, the temporal self-attention module is utilized to capture the temporal dynamics of the fingers and the entire hand.  ...  [9] devise a Dynamic Graph-Based Spatial-Temporal Attention method for hand gesture recognition. They construct a fully-connected graph for all hand joints.  ... 
arXiv:2106.13391v1 fatcat:vahfrfkxyvgk3gizv53nvojokm

Spatial Attention-Based 3D Graph Convolutional Neural Network for Sign Language Recognition

Muneer Al-Hammadi, Mohamed A. Bencherif, Mansour Alsulaiman, Ghulam Muhammad, Mohamed Amine Mekhtiche, Wadood Abdul, Yousef A. Alohali, Tareq S. Alrayes, Hassan Mathkour, Mohammed Faisal, Mohammed Algabri, Hamdi Altaheri (+2 others)
2022 Sensors  
This study presents an efficient architecture for sign language recognition based on a convolutional graph neural network (GCN).  ...  Furthermore, the attention mechanism enhances the spatial context representation of the gestures. The proposed architecture is evaluated on different datasets and shows outstanding results.  ...  For instance, Spatial-Temporal Graph Convolutional Network (ST-GCN) is the basis for many graph-based systems for sign language recognition [29] .  ... 
doi:10.3390/s22124558 pmid:35746341 pmcid:PMC9227856 fatcat:o7nvq762rfe75eekm6bgkyxepq

Skeleton Aware Multi-modal Sign Language Recognition [article]

Songyao Jiang, Bin Sun, Lichen Wang, Yue Bai, Kunpeng Li, Yun Fu
2021 arXiv   pre-print
Specifically, we propose a Sign Language Graph Convolution Network (SL-GCN) to model the embedded dynamics and a novel Separable Spatial-Temporal Convolution Network (SSTCN) to exploit skeleton features  ...  Recently, skeleton-based action recognition attracts increasing attention due to the independence between the subject and background variation.  ...  Specifically, we construct a skeleton graph for SLR using graph reduction and propose a SL-GCN to model the embedded spatial and temporal dynamics.  ... 
arXiv:2103.08833v5 fatcat:dl7aebwtxbam5ftpjkgaaa5pae

Towards Generalizable Surgical Activity Recognition Using Spatial Temporal Graph Convolutional Networks [article]

Duygu Sarikaya, Pierre Jannin
2020 arXiv   pre-print
The proposed modality is based on spatial temporal graph representations of surgical tools in videos, for surgical activity recognition.  ...  Our experiments show that learned spatial temporal graph representations perform well in surgical gesture recognition even when used individually.  ...  Spatial Temporal Graph Construction For each video segment, we construct an undirected spatial temporal graph G = (V, E) to represent the joints over temporal sequences of frames.  ... 
arXiv:2001.03728v4 fatcat:f2azlpri3jhcbhth576nluzzxy

Tesla-Rapture: A Lightweight Gesture Recognition System from mmWave Radar Point Clouds [article]

Dariush Salami, Ramin Hasibi, Sameera Palipana, Petar Popovski, Tom Michoel, Stephan Sigg
2021 arXiv   pre-print
We present Tesla-Rapture, a gesture recognition interface for point clouds generated by mmWave Radars.  ...  State of the art gesture recognition models are either too resource consuming or not sufficiently accurate for integration into real-life scenarios using wearable or constrained equipment such as IoT devices  ...  ACKNOWLEDGMENT We thank the anonymous referees for the constructive feedback provided.  ... 
arXiv:2109.06448v1 fatcat:2s6qp75uj5fsnkv3z72h2d43lq

Deformable Pose Traversal Convolution for 3D Action and Gesture Recognition [chapter]

Junwu Weng, Mengyuan Liu, Xudong Jiang, Junsong Yuan
2018 Lecture Notes in Computer Science  
The representation of 3D pose plays a critical role for 3D action and gesture recognition.  ...  This deformable convolution better utilizes the contextual joints for action and gesture recognition and is more robust to noisy joints.  ...  It models the temporal dynamics of key combinations of joints. Related Work 3D Action and Gesture Recognition 3D action and gesture recognition task attracts a lot of attention in these years.  ... 
doi:10.1007/978-3-030-01234-2_9 fatcat:fhnrpe5qm5blzoygd6j3jnjonm

Skeleton-Based Hand Gesture Recognition by Learning SPD Matrices with Neural Networks [article]

Xuan Nguyen, Luc Brun, Olivier Lezoray, Sébastien Bougleux
2019 arXiv   pre-print
We model the hand skeleton as a graph and introduce a neural network for SPD matrix learning, taking as input the 3D coordinates of hand joints.  ...  For gesture recognition, we train a linear SVM classifier using features extracted from our network.  ...  [34] introduced a Spatial Temporal Graph CNN operating on a graph constructed from body joints and physical connections between them.  ... 
arXiv:1905.07917v1 fatcat:57nxkyxrlnby3ckbgzi4mvg4di

A Neural Network Based on SPD Manifold Learning for Skeleton-Based Hand Gesture Recognition

Xuan Son Nguyen, Luc Brun, Olivier Lezoray, Sebastien Bougleux
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
We thank Guillermo Garcia-Hernando for providing access to FPHA dataset [12] .  ...  The Proposed Approach In this section, we present our network model referred to as Spatial-Temporal and Temporal-Spatial Hand Gesture Recognition Network (ST-TS-HGR-NET).  ...  modeling for hand gesture recognition, while temporal modeling is not considered in [54] as they focus on image classification tasks.  ... 
doi:10.1109/cvpr.2019.01231 dblp:conf/cvpr/NguyenBLB19 fatcat:bcjpypulazcjdil72r5iouubfi

A Deep Learning-based Multimodal Depth-Aware Dynamic Hand Gesture Recognition System [article]

Hasan Mahmud, Mashrur M. Morshed, Md. Kamrul Hasan
2021 arXiv   pre-print
The dynamic hand gesture recognition task has seen studies on various unimodal and multimodal methods.  ...  In this paper, we revisit this approach to hand gesture recognition and suggest several improvements. We observe that raw depth images possess low contrast in the hand regions of interest (ROI).  ...  We hope that our work fuels further research in the field of multimodal dynamic hand gesture recognition.  ... 
arXiv:2107.02543v2 fatcat:uqaqdyypwrervagh2oet7hragm

Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition [article]

Zitong Yu, Benjia Zhou, Jun Wan, Pichao Wang, Haoyu Chen, Xin Liu, Stan Z. Li, Guoying Zhao
2020 arXiv   pre-print
for gesture recognition.  ...  Gesture recognition has attracted considerable attention owing to its great potential in applications.  ...  level, which is able to model fine-grained temporal dynamics for gesture recognition.  ... 
arXiv:2008.09412v1 fatcat:vphe2saxbjhxtee2twdkbby3yi

RGB-D-based Human Motion Recognition with Deep Learning: A Survey [article]

Pichao Wang and Wanqing Li and Philip Ogunbona and Jun Wan and Sergio Escalera
2018 arXiv   pre-print
Particularly, we highlighted the methods of encoding spatial-temporal-structural information inherent in video sequence, and discuss potential directions for future research.  ...  Human motion recognition is one of the most important branches of human-centered research activities. In recent years, motion recognition based on RGB-D data has attracted much attention.  ...  [16] for hand gestures and [172] for action recognition).  ... 
arXiv:1711.08362v2 fatcat:cugugpqeffcshnwwto4z2aw4ti

A neural network based on SPD manifold learning for skeleton-based hand gesture recognition [article]

Xuan Son Nguyen and Luc Brun and Olivier Lézoray and Sébastien Bougleux
2019 arXiv   pre-print
This paper proposes a new neural network based on SPD manifold learning for skeleton-based hand gesture recognition.  ...  The second stage relies on different architectures for spatial and temporal Gaussian aggregation of joint features. The third stage learns a final SPD matrix from skeletal data.  ...  We thank Guillermo Garcia-Hernando for providing access to FPHA dataset [12] .  ... 
arXiv:1904.12970v1 fatcat:hv2rjb5jnbeapd5vvf7ula6fsa

American Sign Language Words Recognition using Spatio-Temporal Prosodic and Angle Features: A sequential learning approach

Sunusi Bala Abdullahi, Kosin Chamnongthai
2022 IEEE Access  
The performance of our FFV-Bi-LSTM is further evaluated on ASL data set, leap motion dynamic hand gestures data set (LMDHG), and Semaphoric hand gestures contained in the Shape Retrieval Contest (SHREC  ...  cross-validation on the constructed dataset.  ...  We are also grateful to the anonymous IEEE Access reviewers for their potential reviews and insightful comments.  ... 
doi:10.1109/access.2022.3148132 fatcat:wkaj6r4sdbgwdix4iujtqga3ni

Graph-based Spatial-temporal Feature Learning for Neuromorphic Vision Sensing [article]

Yin Bi, Aaron Chadha, Alhabib Abbas, Eirina Bourtsoulatze, Yiannis Andreopoulos
2019 arXiv   pre-print
We extend this with our proposed Graph2Grid block and temporal feature learning module for efficiently modelling temporal dependencies over multiple graphs and a long temporal extent.  ...  The core of our framework comprises a spatial feature learning module, which utilizes residual-graph convolutional neural networks (RG-CNN), for end-to-end learning of appearance-based features directly  ...  For action recognition and action similarity labeling, we model coarse temporal dependencies over multiple graphs by converting to a grid representation via the Graph2Grid module and perform temporal feature  ... 
arXiv:1910.03579v2 fatcat:v3brpgoezrgzzf57ncmy4vm6eu

Skeleton Graph-Neural-Network-Based Human Action Recognition: A Survey

Miao Feng, Jean Meunier
2022 Sensors  
This paper provides an up-to-date review for readers on skeleton graph-neural-network-based human action recognition.  ...  Connecting the skeleton joints as in the physical appearance can naturally generate a graph.  ...  Finally, they computed the sum of the output from both local and global graphs. Y. Li et al. [70] focused on hand gesture recognition.  ... 
doi:10.3390/s22062091 pmid:35336262 pmcid:PMC8952863 fatcat:ku6vp3olffgirgxpkns6avc5qa
« Previous Showing results 1 — 15 out of 3,505 results