Login / Signup
FTAN: Frame-to-frame temporal alignment network with contrastive learning for few-shot action recognition.
Bin Yu
Yonghong Hou
Zihui Guo
Zhiyi Gao
Yueyang Li
Published in:
Image Vis. Comput. (2024)
Keyphrases
</>
action recognition
human actions
human detection
video frames
activity recognition
learning algorithm
wireless sensor networks
body parts
computer vision
d scene
key frames
spatial temporal
mid level
human activity recognition