I3D-Shufflenet Based Human Action Recognition

I3D-Shufflenet Based Human Action Recognition

In view of difficulty in application of optical flow based human action recognition due to large amount of calculation, a human action recognition algorithm I3D-shufflenet model is proposed combining the advantages of I3D neural network and lightweight model shufflenet. The 5 × 5 convolution kernel...

Full description

Bibliographic Details
Main Authors:	Guocheng Liu, Caixia Zhang, Qingyang Xu, Ruoshi Cheng, Yong Song, Xianfeng Yuan, Jie Sun
Format:	Article
Language:	English
Published:	MDPI AG 2020-11-01
Series:	Algorithms
Subjects:	action recognition 3D convolution I3D neural network shufflenet
Online Access:	https://www.mdpi.com/1999-4893/13/11/301

Similar Items

AR3D: Attention Residual 3D Network for Human Action Recognition
by: Min Dong, et al.
Published: (2021-02-01)

Skeleton-Based Square Grid for Human Action Recognition With 3D Convolutional Neural Network
by: Wenwen Ding, et al.
Published: (2021-01-01)

Internal Transfer Learning for Improving Performance in Human Action Recognition for Small Datasets
by: Tian Wang, et al.
Published: (2017-01-01)

Review of Human Action Recognition Based on Deep Learning
by: QIAN Huifang, YI Jianping, FU Yunhu
Published: (2021-03-01)

Human Action Monitoring for Healthcare Based on Deep Learning
by: Yongbin Gao, et al.
Published: (2018-01-01)

Human action recognition using support vector machines and 3D convolutional neural networks
by: Majd Latah
Published: (2017-03-01)

Deep Learning Methods for Human Action Recognition
by: Yu, Zeqi
Published: (2021)

Service Action Recognition in Power Supply Business Hall with 3D-Fused ConvNet
by: Tongyao Lin, et al.
Published: (2021-01-01)

3D-CNN-Based Fused Feature Maps with LSTM Applied to Action Recognition
by: Sheeraz Arif, et al.
Published: (2019-02-01)

Video-Based Human Action Recognition Using Spatial Pyramid Pooling and 3D Densely Convolutional Networks
by: Wanli Yang, et al.
Published: (2018-11-01)

Volumetric Object Recognition Using 3-D CNNs on Depth Data
by: Ali Caglayan, et al.
Published: (2018-01-01)

Multimodal Gesture Recognition Using 3-D Convolution and Convolutional LSTM
by: Guangming Zhu, et al.
Published: (2017-01-01)

An Automated Training of Deep Learning Networks by 3D Virtual Models for Object Recognition
by: Kamil Židek, et al.
Published: (2019-04-01)

Inter-Dimensional Correlations Aggregated Attention Network for Action Recognition
by: Xiaochao Li, et al.
Published: (2021-01-01)

Action Recognition Using Deep 3D CNNs with Sequential Feature Aggregation and Attention
by: Fazliddin Anvarov, et al.
Published: (2020-01-01)

Efficient Parallel Inflated 3D Convolution Architecture for Action Recognition
by: Yukun Huang, et al.
Published: (2020-01-01)

Gaze-Assisted Multi-Stream Deep Neural Network for Action Recognition
by: Yinan Liu, et al.
Published: (2017-01-01)

A Hybrid Network for Large-Scale Action Recognition from RGB and Depth Modalities
by: Huogen Wang, et al.
Published: (2020-06-01)

Spatiotemporal Relation Networks for Video Action Recognition
by: Zheng Liu, et al.
Published: (2019-01-01)

TUHAD: Taekwondo Unit Technique Human Action Dataset with Key Frame-Based CNN Action Recognition
by: Jinkue Lee, et al.
Published: (2020-08-01)

MSST-RT: Multi-Stream Spatial-Temporal Relative Transformer for Skeleton-Based Action Recognition
by: Yan Sun, et al.
Published: (2021-08-01)

Spatiotemporal Interaction Residual Networks with Pseudo3D for Video Action Recognition
by: Jianyu Chen, et al.
Published: (2020-06-01)

Action Recognition in Videos Using Pre-Trained 2D Convolutional Neural Networks
by: Jun-Hwa Kim, et al.
Published: (2020-01-01)

Action Recognition Network Using Stacked Short-Term Deep Features and Bidirectional Moving Average
by: Jinsol Ha, et al.
Published: (2021-06-01)

MVCLN: Multi-View Convolutional LSTM Network for Cross-Media 3D Shape Recognition
by: Qi Liang, et al.
Published: (2020-01-01)

A 3D-CNN and LSTM Based Multi-Task Learning Architecture for Action Recognition
by: Xi Ouyang, et al.
Published: (2019-01-01)

GAS-GCN: Gated Action-Specific Graph Convolutional Networks for Skeleton-Based Action Recognition
by: Wensong Chan, et al.
Published: (2020-06-01)

Recognition of Rare Low-Moral Actions Using Depth Data
by: Kanghui Du, et al.
Published: (2020-05-01)

Deep-Aligned Convolutional Neural Network for Skeleton-Based Action Recognition and Segmentation
by: Babak Hosseini, et al.
Published: (2020-05-01)

Abnormal Behavior Detection in Uncrowded Videos with Two-Stream 3D Convolutional Neural Networks
by: Abid Mehmood
Published: (2021-04-01)

MVPN: Multi-View Prototype Network for 3D Shape Recognition
by: Zizhao Wu, et al.
Published: (2019-01-01)

Spatiotemporal Convolutional Neural Network with Convolutional Block Attention Module for Micro-Expression Recognition
by: Boyu Chen, et al.
Published: (2020-07-01)

ASNet: Auto-Augmented Siamese Neural Network for Action Recognition
by: Yujia Zhang, et al.
Published: (2021-07-01)

Action recognition based on binocular vision
by: Yiwei Ru, et al.
Published: (2017-05-01)

Temporal Modeling on Multi-Temporal-Scale Spatiotemporal Atoms for Action Recognition
by: Guangle Yao, et al.
Published: (2018-10-01)

Deep Spatiotemporal Relation Learning With 3D Multi-Level Dense Fusion for Video Action Recognition
by: Junxuan Zhang, et al.
Published: (2019-01-01)

Action Recognition Using Attention-Joints Graph Convolutional Neural Networks
by: Tasweer Ahmad, et al.
Published: (2020-01-01)

Metric-Based Attention Feature Learning for Video Action Recognition
by: Dae Ha Kim, et al.
Published: (2021-01-01)

Deep Learning-Based Action Recognition Using 3D Skeleton Joints Information
by: Nusrat Tasnim, et al.
Published: (2020-09-01)

Low-Cost Network Scheduling of 3D-CNN Processing for Embedded Action Recognition
by: Hyunhoon Lee, et al.
Published: (2021-01-01)