Ensembled Transfer Learning Based Multichannel Attention Networks for Human Activity Recognition in Still Images

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE Access Ročník 10; s. 47051 - 47062
Hlavní autoři:	Koki Hirooka, Md. Al Mehedi Hasan, Jungpil Shin, Azmain Yakin Srizon
Médium:	Journal Article
Jazyk:	japonština
Vydáno:	Institute of Electrical and Electronics Engineers (IEEE) 01.01.2022
Témata:	Action Recognition Artificial intelligence Channel (broadcasting) Computer network Computer science Computer Vision and Pattern Recognition Convolutional neural network Deep learning Deep Learning in Computer Vision and Image Recognition Electrical engineering. Electronics. Nuclear engineering ensembling Feature (linguistics) Feature extraction Foreground Segmentation FOS: Languages and literature FOS: Philosophy, ethics and religion Human Action Recognition and Pose Estimation Human Activity Analysis Human activity recognition InceptionResnetV2 InceptionV3 Linguistics Machine learning Margin (machine learning) Motion Detection multi-channel attention module Multiple Object Tracking Pattern recognition (psychology) Philosophy Physical Sciences TK1-9971 Transfer of learning Visual Object Tracking and Person Re-identification Xception
ISSN:	2169-3536
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
ISSN:	2169-3536
DOI:	10.60692/xa489-zdz82