Human Activity Recognition Using Cascaded Dual Attention CNN and Bi-Directional GRU Framework

Vision-based human activity recognition (HAR) has emerged as one of the essential research areas in video analytics. Over the last decade, numerous advanced deep learning algorithms have been introduced to recognize complex human actions from video streams. These deep learning algorithms have shown...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Journal of imaging Ročník 9; číslo 7; s. 130
Hlavní autoři:	Ullah, Hayat, Munir, Arslan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Switzerland MDPI AG 26.06.2023 MDPI
Témata:	Accuracy activity recognition Algorithms Analysis Artificial intelligence Artificial neural networks channel–spatial attention Computational efficiency Computing time convolutional neural network Data mining Datasets Deep learning Effectiveness Feature maps Frames (data processing) Frames per second gated recurrent unit Hands Human activity recognition Human acts Human behavior Internet of Things Machine learning Methods Model accuracy Neural networks pattern recognition Robustness (mathematics) Surveillance Video data United States deep learning gated recurrent unit convolutional neural network activity recognition channel–spatial attention pattern recognition
ISSN:	2313-433X, 2313-433X
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!