Filters








17 Hits in 2.5 sec

EV-Action: Electromyography-Vision Multi-Modal Action Dataset [article]

Lichen Wang, Bin Sun, Joseph Robinson, Taotao Jing, Yun Fu
2020 arXiv   pre-print
The details of EV-Action dataset are clarified, meanwhile, a simple yet effective framework for EMG-based action recognition is proposed.  ...  To make up this, we introduce a new, large-scale EV-Action dataset in this work, which consists of RGB, depth, electromyography (EMG), and two skeleton modalities.  ...  Thus, the EMG modality could both improve our current action recognition capabilities and serve as a necessity for certain applications. A.  ... 
arXiv:1904.12602v2 fatcat:jozqgr5d55dknpsfiu6tnlijca

Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks [article]

Lei Shi, Yifan Zhang, Jian Cheng, Hanqing LU
2019 arXiv   pre-print
Second, the second-order information of the skeleton data, i.e., the length and orientation of the bones, is rarely investigated, which is naturally more informative and discriminative for the human action  ...  In this work, we propose a novel multi-stream attention-enhanced adaptive graph convolutional neural network (MS-AAGCN) for skeleton-based action recognition.  ...  datasets for skeleton-based action recognition.  ... 
arXiv:1912.06971v1 fatcat:2hotk5vbqjb3riilvj3niv72ce

A tri‐attention enhanced graph convolutional network for skeleton‐based action recognition

Xingming Li, Wei Zhai, Yang Cao
2021 IET Computer Vision  
Skeleton-based action recognition has recently attracted a lot of research interests due to its advantage in computational efficiency.  ...  of each domain. iii) A fusion unit is presented to integrate the features of these three domains together and leverage as orientation for graph convolution at each layer.  ...  However, as a contrast, the significant variations across local movements can serve as discriminate cues for action recognition.  ... 
doi:10.1049/cvi2.12017 fatcat:pxpp7uv3zbgm3lassnpoansizi

Fusing Higher-Order Features in Graph Neural Networks for Skeleton-Based Action Recognition [article]

Zhenyue Qin and Yang Liu and Pan Ji and Dongwoo Kim and Lei Wang and Bob McKay and Saeed Anwar and Tom Gedeon
2021 arXiv   pre-print
Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues, using these representations in a graph neural network for feature fusion to boost recognition  ...  Skeleton sequences are lightweight and compact, thus are ideal candidates for action recognition on edge devices.  ...  NTU60 is a widely-used benchmark dataset for skeleton-based action recognition, incorporating 56,000 IV: A comparison of the effect for improving action recognition by concatenating certain angular feature  ... 
arXiv:2105.01563v4 fatcat:oxzgap7efraqznhsqkkzl2rmwy

ANUBIS: Skeleton Action Recognition Dataset, Review, and Benchmark [article]

Zhenyue Qin, Yang Liu, Madhawa Perera, Tom Gedeon, Pan Ji, Dongwoo Kim, Saeed Anwar
2022 arXiv   pre-print
We aim to provide a roadmap for new and existing researchers a on the landscapes of skeleton-based action recognition for new and existing researchers.  ...  To this end, we present a review in the form of a taxonomy on existing works of skeleton-based action recognition.  ...  • We collect a large-scale human skeleton dataset named ANUBIS. Using this dataset, we benchmark a variety of existing approaches for skeleton-based action recognition.  ... 
arXiv:2205.02071v3 fatcat:22iwew3p4faqxfp2ozbehyeffu

A Benchmark for Gait Recognition under Occlusion Collected by Multi-Kinect SDAS [article]

Na Li, Xinbo Zhao
2021 arXiv   pre-print
Besides, as human pose is less sensitive to occlusion than human appearance, we propose a novel gait recognition method SkeletonGait based on human dual skeleton model using a framework of siamese spatio-temporal  ...  Human gait is one of important biometric characteristics for human identification at a distance. In practice, occlusion usually occurs and seriously affects accuracy of gait recognition.  ...  Besides, we propose a novel model-based gait recognition method called SkeletonGait, which learns more discriminative gait information from the human dual skeleton model based on siamese-STGCN.  ... 
arXiv:2107.08990v1 fatcat:pv7k5p523rhu5i6cbjpvgl6ffi

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.  ...  After analyzing previous related studies, a new taxonomy for skeleton-GNN-based methods is proposed according to their designs, and their merits and demerits are analyzed.  ...  [130] proposed a temporal attention module (TAM) to increase the efficiency in skeleton-based action recognition.  ... 
doi:10.3390/s22062091 pmid:35336262 pmcid:PMC8952863 fatcat:ku6vp3olffgirgxpkns6avc5qa

A Self-Attention Augmented Graph Convolutional Clustering Networks for Skeleton-Based Video Anomaly Behavior Detection

Chengming Liu, Ronghua Fu, Yinghao Li, Yufei Gao, Lei Shi, Weiwei Li
2021 Applied Sciences  
In this paper, we propose a new method for detecting abnormal human behavior based on skeleton features using self-attention augment graph convolution.  ...  The skeleton data have been proved to be robust to the complex background, illumination changes, and dynamic camera scenes and are naturally constructed as a graph in non-Euclidean space.  ...  Skeleton-Based Action Recognition Most of the conventional techniques for skeleton-based action recognition generally rely on hand-crafted features to model the human body [24] [25] [26] .  ... 
doi:10.3390/app12010004 fatcat:2cufica45rapfluo74b4563ezu

Detection of Physical Strain and Fatigue in Industrial Environments Using Visual and Non-Visual Low-Cost Sensors

Konstantinos Papoutsakis, George Papadopoulos, Michail Maniadakis, Thodoris Papadopoulos, Manolis Lourakis, Maria Pateraki, Iraklis Varlamis
2022 Technologies  
In addition a time lagging correlation between the estimated ergonomic risks for physical strain and high heart rate was assessed using a larger dataset of synchronous visual and heart rate data sequences  ...  Moreover, a new multi-modal dataset of video and heart rate data captured in a real manufacturing workplace during car door assembly activities is introduced.  ...  Acknowledgments: The authors thank Consortium partner Stellantis-Centro Ricerche FIAT (CRF)/ SPW Research & Innovation department in Melfi, Italy, for their valuable feedback in the implementation and  ... 
doi:10.3390/technologies10020042 fatcat:v5c6zwqueneqdbq6exsjxzt4im

Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognition [article]

Ning Wang, Guangming Zhu, Liang Zhang, Peiyi Shen, Hongsheng Li, Cong Hua
2021 arXiv   pre-print
For a given video-based Human-Object Interaction scene, modeling the spatio-temporal relationship between humans and objects are the important cue to understand the contextual information presented in  ...  The full use of appearance features, the spatial location and the semantic information are also the key to improve the video-based Human-Object Interaction recognition performance.  ...  As claimed ahead, change means actions. To capture the changing orientations of human/objects ahead is helpful for HOI recognition.  ... 
arXiv:2108.08633v1 fatcat:ha4t45ofurgcjey3izbp5fa3vm

Continuous Human Action Recognition for Human-Machine Interaction: A Review [article]

Harshala Gammulle, David Ahmedt-Aristizabal, Simon Denman, Lachlan Tychsen-Smith, Lars Petersson, Clinton Fookes
2022 arXiv   pre-print
Recognising actions and detecting action transitions within an input video are challenging but necessary tasks for applications that require real-time human-machine interaction.  ...  With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams.  ...  YOLOv3-SPP is a revised YOLOv3, which has one SPP module [83] in front of its first detection header. [167] Faster R-CNN Skeleton-based (STGCN [168] ) CAD120 Object detector as feature extractor; Dataset  ... 
arXiv:2202.13096v1 fatcat:mczyeb5vyfgxdiubjhklwjrtlm

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future [article]

David Ahmedt-Aristizabal, Mohammad Ali Armin, Simon Denman, Clinton Fookes, Lars Petersson
2021 arXiv   pre-print
We also outline the limitations of existing techniques and discuss potential directions for future research.  ...  them as a matrix.  ...  Graph representations for skeleton-based action recognition are gaining importance in the last couple of years.  ... 
arXiv:2105.13137v1 fatcat:gm7d2ziagba7bj3g34u4t3k43y

Graph Neural Networks in IoT: A Survey [article]

Guimin Dong, Mingyue Tang, Zhiyuan Wang, Jiechao Gao, Sikun Guo, Lihua Cai, Robert Gutierrez, Bradford Campbell, Laura E. Barnes, Mehdi Boukhechba
2022 arXiv   pre-print
Continuous sensing generates massive amounts of data and presents challenges for machine learning.  ...  In this survey, we present a comprehensive review of recent advances in the application of GNNs to the IoT field, including a deep dive analysis of GNN design in various IoT sensing environments, an overarching  ...  [13] summarized the applications of GNNs in human action recognition work, where graph models are applied to represent the non-Euclidean body skeleton.  ... 
arXiv:2203.15935v2 fatcat:jkqg5ukg5fezbewu5mr5hqsp4e

Neural Information Processing Techniques for Skeleton-Based Action Recognition [article]

Zhenyue Qin, University, The Australian National
2022
Recently, skeleton-based action recognition, as a subarea of action recognition, is swiftly accumulating attention and popularity.  ...  This problem lays the technical foundations for a wide range of applications, such as human-robot interaction, virtual reality, sports analysis, and so on.  ...  using a manually defined structure for skeleton-based action recognition.  ... 
doi:10.25911/2s2d-cj45 fatcat:t3qz3pnat5a2tj2z7lawz6rcry

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

David Ahmedt-Aristizabal, Mohammad Ali Armin, Simon Denman, Clinton Fookes, Lars Petersson
2021 Sensors  
We also outline the limitations of existing techniques and discuss potential directions for future research.  ...  them as a matrix.  ...  Graph representations for skeleton-based action recognition are gaining prominence over the last couple of years.  ... 
doi:10.3390/s21144758 fatcat:jytyt4u2pjgvhnhcto3vcvd3a4
« Previous Showing results 1 — 15 out of 17 results