Distilled 3-D (D3D) networks for video action recognition

A team of researchers at Google, the University of Michigan and Princeton University have recently developed a new method for video action recognition. Video action recognition entails identifying particular actions performed in video footage, such as opening a door, closing a door, etc.

from News on Artificial Intelligence and Machine Learning http://bit.ly/2FimloV
SHARE
    Blogger Comment
    Facebook Comment

0 comments:

Post a Comment