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

Human activity recognition is one of the most difficult tasks in computer vision. Due to the lack of time information, detecting human activities from still photos is more difficult than sensor-based or video-based techniques. Recently, various deep learning based solutions are being proposed one af...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Koki Hirooka, Md. Al Mehedi Hasan, Jungpil Shin, Azmain Yakin Srizon
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	IEEE 2022-01-01
סדרה:	IEEE Access
נושאים:	Human activity recognition multi-channel attention module ensembling InceptionV3 Xception InceptionResnetV2
גישה מקוונת:	https://ieeexplore.ieee.org/document/9765465/
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!