Filters








972 Hits in 4.1 sec

GAS-GCN: Gated Action-Specific Graph Convolutional Networks for Skeleton-Based Action Recognition

Wensong Chan, Zhiqiang Tian, Yang Wu
2020 Sensors  
Skeleton-based action recognition has achieved great advances with the development of graph convolutional networks (GCNs).  ...  In addition, to filter out the useless and redundant information in the temporal dimension, we propose a simple yet effective operation named gated temporal convolution.  ...  network for skeleton-based action recognition.  ... 
doi:10.3390/s20123499 pmid:32575802 fatcat:aczc3nt3ivetxnztys27i5q77y

Structure-Feature Fusion Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition

Zhitao Zhang, Zhengyou Wang, Shanna Zhuang, Fuyu Huang
2020 IEEE Access  
(RNNs), convolution neural networks (CNNs) or graph convolutional networks(GCNs).  ...  SKELETON-BASED ACTION RECOGNITION Traditional methods of skeleton-based action recognition mainly focus on hand-crafted features.  ... 
doi:10.1109/access.2020.3046142 fatcat:xnk4hwfxxbeoffcnfcyvovqhaq

An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition [article]

Chenyang Si, Wentao Chen, Wei Wang, Liang Wang, Tieniu Tan
2019 arXiv   pre-print
In this paper, we propose a novel Attention Enhanced Graph Convolutional LSTM Network (AGC-LSTM) for human action recognition from skeleton data.  ...  Skeleton-based action recognition is an important task that requires the adequate understanding of movement characteristics of a human action from the given skeleton sequence.  ...  The Convolutional Neural Networks (CNNs) are used to learn spatial-temporal features from skeletons in [4, 14, 10] . [39, 26] employ graph convolutional networks (GCN) for action recognition.  ... 
arXiv:1902.09130v2 fatcat:v5my74xbsbcbbes5vnxhgellie

A Survey on 3D Skeleton-Based Action Recognition Using Learning Method [article]

Bin Ren, Mengyuan Liu, Runwei Ding, Hong Liu
2020 arXiv   pre-print
Then a comprehensive introduction about Recurrent Neural Network(RNN)-based, Convolutional Neural Network(CNN)-based and Graph Convolutional Network(GCN)-based main stream action recognition techniques  ...  3D skeleton-based action recognition, owing to the latent advantages of skeleton, has been an active topic in computer vision.  ...  CNN Based Methods Convolutional neural networks have also been applied to the skeleton-based action recognition.  ... 
arXiv:2002.05907v1 fatcat:tmnfwxnwtrdo3hjncdoxqvdowy

Prediction of Human Activities Based on a New Structure of Skeleton Features and Deep Learning Model

Neziha Jaouedi, Francisco J. Perales, José Maria Buades, Noureddine Boujnah, Med Salim Bouhlel
2020 Sensors  
In this paper, we present a novel approach to human activity recognition from videos using the Recurrent Neural Network (RNN) for activity classification and the Convolutional Neural Network (CNN) with  ...  a new structure of the human skeleton to carry out feature presentation.  ...  Table 1 . 1 Cont. : Convolutional Neural Network, GRU: Gated Recurrent Units, LOM: Local Occupation Model, LSTM: Long Short Term Memory, RCN: Recurrent Convolution Networks, RNN: Recurrent Neural Network  ... 
doi:10.3390/s20174944 pmid:32882884 fatcat:wju6gvbiibchhno5r4c733uloy

Gesture Recognition Based on 3D Human Pose Estimation and Body Part Segmentation for RGB Data Input

Ngoc-Hoang Nguyen, Tran-Dac-Thinh Phan, Guee-Sang Lee, Soo-Hyung Kim, Hyung-Jeong Yang
2020 Applied Sciences  
Extracted from the RGB images are the multimodal input observations, which are combined by multi-modal stream networks suited to different input modalities: residual 3D convolutional neural networks based  ...  on ResNet architecture (3DCNN_ResNet) for RGB images and color body part segmentation modalities; long short-term memory network (LSTM) for 3D skeleton joint modality.  ...  The development of deep learning methods based on a convolution neural network (CNN) and recurrent neural network (RNN) or long short-term memory network (LSTM) have achieved positive results in handling  ... 
doi:10.3390/app10186188 fatcat:sdygawbngncjtinuek225vgzoy

Two-stream RNN/CNN for action recognition in 3D videos

Rui Zhao, Haider Ali, Patrick van der Smagt
2017 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
We demonstrate superior results by a system which combines recurrent neural networks with convolutional neural networks in a voting approach.  ...  The gated-recurrent-unit-based neural networks are particularly well-suited to distinguish actions based on long-term information from optical tracking data; the 3D-CNNs focus more on detailed, recent  ...  Our proposed deep-learning methods consist mainly of three parts: a novel skeleton-based recurrent neural network structure, using a 3D-convolutional [8] neural network for RGB videos, and sketching  ... 
doi:10.1109/iros.2017.8206288 dblp:conf/iros/ZhaoAS17 fatcat:r4grezv5wvgxhm6ajxnm3i5apa

Skeleton-Based Emotion Recognition Based on Two-Stream Self-Attention Enhanced Spatial-Temporal Graph Convolutional Network

Jiaqi Shi, Chaoran Liu, Carlos Toshinori Ishi, Hiroshi Ishiguro
2020 Sensors  
Some studies in action recognition have applied graph-based neural networks to explicitly model the spatial connection between joints.  ...  We propose a self-attention enhanced spatial temporal graph convolutional network for skeleton-based emotion recognition, in which the spatial convolutional part models the skeletal structure of the body  ...  of the human bones, has also been proved to be useful for skeleton-based action recognition tasks.  ... 
doi:10.3390/s21010205 pmid:33396917 pmcid:PMC7795329 fatcat:pqxk3jadnrhhhkpzngfn2cuiva

Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition [article]

Hong Liu and Juanhui Tu and Mengyuan Liu
2017 arXiv   pre-print
Although most recent action recognition methods are based on Recurrent Neural Networks which present outstanding performance, one of the shortcomings of these methods is the tendency to overemphasize the  ...  To our best knowledge, this is the first application of 3D CNN in skeleton-based action recognition. Our method consists of three stages.  ...  RNN-based Methods Most recent action recognition methods are based on Recurrent Neural Networks and Long-Short Term Memory in some form. Du et al.  ... 
arXiv:1705.08106v2 fatcat:lebbvcc4qjbhtfqwnafcz5nyde

Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition [article]

Jinfeng Wei, Yunxin Wang, Mengli Guo, Pei Lv, Xiaoshan Yang, Mingliang Xu
2021 arXiv   pre-print
Graph convolutional networks (GCNs) based methods have achieved advanced performance on skeleton-based action recognition task.  ...  In this work, we propose a novel dynamic hypergraph convolutional networks (DHGCN) for skeleton-based action recognition.  ...  Skeleton-based action recognition learning for skeleton-based action recognition using with gated convolutional neural networks. IEEE temporal sliding lstm networks.  ... 
arXiv:2112.10570v1 fatcat:x2564jl4dngmhba7duxf5yai6m

Skeleton based Activity Recognition by Fusing Part-wise Spatio-temporal and Attention Driven Residues [article]

Chhavi Dhiman, Dinesh Kumar Vishwakarma, Paras Aggarwal
2019 arXiv   pre-print
In this paper, we present a novel skeleton-based part-wise Spatiotemporal CNN RIAC Network-based 3D human action recognition framework to visualise the action dynamics in part wise manner and utilise each  ...  To extract and learn salient features for action recognition, attention driven residues are used which enhance the performance of residual components for effective 3D skeleton-based Spatio-temporal action  ...  Therefore to solve the problem of skeleton-based action recognition for large inter-class similarity Residual Inception Attention-based Convolution Network (RIAC-Net), Fig. 2 , is designed which is  ... 
arXiv:1912.00576v1 fatcat:4pg77axdxbd43p6sa6lt6fmnoe

Spatial–temporal graph neural network based on node attention

Qiang Li, Jun Wan, Wucong Zhang, Qian Long Kweh
2022 Applied Mathematics and Nonlinear Sciences  
Recently, the method of using graph neural network based on skeletons for action recognition has become more and more popular, due to the fact that a skeleton can carry very intuitive and rich action information  ...  The spatial–temporal graph convolutional neural network (ST-GCN) is a dynamic skeleton model that automatically learns spatial–temporal model from data, which not only has stronger expression ability,  ...  Related work With the rapid development of human pose estimation and graph neural network, now most common action recognition methods which are based on skeleton can be categorised into three methods:  ... 
doi:10.2478/amns.2022.1.00005 fatcat:tuuwp44dlbh2jpbaswb7xfpzki

RGB-D Data-Based Action Recognition: A Review

Muhammad Bilal Shaikh, Douglas Chai
2021 Sensors  
Naturally, each action-data modality—such as RGB, depth, skeleton, and infrared (IR)—has distinct characteristics; therefore, it is important to exploit the value of each modality for better action recognition  ...  The increase in the number of action recognition datasets intersects with advances in deep learning architectures and computational support, both of which offer significant research opportunities.  ...  Recurrent Neural Networks (RNN) The Recurrent Neural Network (RNN), Auto-Associative, or Feedback Network is a type of neural network that has variants including Gated Recurrent units.  ... 
doi:10.3390/s21124246 fatcat:7dvocdy63rckne5yunhfsnr4p4

Remarkable Skeleton Based Human Action Recognition

Sushma Jaiswal, Tarun Jaiswal
2020 Artificial Intelligence Evolution  
Skeleton-based human-action-recognition (SBHAR) has wide applications in cognitive science and automatic surveillance.  ...  However, the most challenging and crucial task of the skeleton-based human-action-recognition (SBHAR) is a significant view variation while capturing the data.  ...  The authors trust the APSR for depth construction and RGB+D based action-recognition. View Adaptation Neural Network (VA-NN).  ... 
doi:10.37256/aie.122020562 fatcat:2wdzis5ax5bdfnwdhlzgvoh6xu

Deep learning‐based action recognition with 3D skeleton: A survey

Yuling Xing, Jia Zhu
2021 CAAI Transactions on Intelligence Technology  
In this survey, we first introduce the development process of 3D skeleton-data action recognition and the classification of graph convolutional network, then introduce the commonly used NTU RGB + D and  ...  Action recognition based on 3D skeleton data has attracted much attention due to its wide application, and it is one of the most popular research topics in computer vision.  ...  For instance, recurrent neural networks (RNNs) with Long-Short Term Memory (LSTM) have been employed to model skeleton data for 3D action recognition [4] [5] [6] [7] .  ... 
doi:10.1049/cit2.12014 fatcat:77vtqpozjnfdrj3qodcbjzgjmq
« Previous Showing results 1 — 15 out of 972 results