А вот про это я уже пару лет рассказываю, но они сделали.
Audiovisual self-supervised representation learning
#SSL #audio #video
Audiovisual self-supervised representation learning
#SSL #audio #video
Meta
Audiovisual self-supervised representation learning
We’re sharing new research on using the natural association between video & sound to teach machines to better understand the world. Our self-supervised approach, which is a #CVPR21 best paper candidate, learns directly from sounds & images in videos.