Dual-attention Network for View-invariant Action Recognition

Dual-attention Network for View-invariant Action Recognition

Abstract View-invariant action recognition has been widely researched in various applications, such as visual surveillance and human–robot interaction. However, view-invariant human action recognition is challenging due to the action occlusions and information loss caused by view changes. Modeling s...

Full description

Bibliographic Details
Main Authors: Gedamu Alemu Kumie, Maregu Assefa Habtie, Tewodros Alemu Ayall, Changjun Zhou, Huawen Liu, Abegaz Mohammed Seid, Aiman Erbad
Format: Article
Language:English
Published: Springer 2023-07-01
Series:Complex & Intelligent Systems
Subjects:
Human action recognition
Self-attention
Cross-attention
Dual-attention
Attention transfer
View-invariant representation
Online Access:https://doi.org/10.1007/s40747-023-01171-8

Similar Items

Similar Items