Deep Neural Networks Using Capsule Networks and Skeleton-Based Attentions for Action Recognition

Deep Neural Networks Using Capsule Networks and Skeleton-Based Attentions for Action Recognition

This work develops Deep Neural Networks (DNNs) by adopting Capsule Networks (CapsNets) and spatiotemporal skeleton-based attention to effectively recognize subject actions from abundant spatial and temporal contexts of videos. The proposed generic DNN includes four 3D Convolutional Neural Networks (...

Full description

Bibliographic Details
Main Authors: Manh-Hung Ha, Oscal Tzyh-Chiang Chen
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Deep neural network
convolutional neural network
recurrent neural network
capsule network
spatiotemporal attention
skeleton
Online Access:https://ieeexplore.ieee.org/document/9312030/

Internet

https://ieeexplore.ieee.org/document/9312030/

Similar Items