Sign in

ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning.

Sangho LeeJiwan ChungYoungjae YuGunhee KimThomas M. BreuelGal ChechikYale Song
Published in: ICCV (2021)
Keyphrases
  • audio visual
  • multi modal
  • video representation
  • principal component analysis
  • image database
  • video objects