Login / Signup

Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization.

Daizong LiuWei Hu
Published in: CoRR (2022)
Keyphrases
  • natural language
  • video classification
  • theoretical framework
  • real time
  • video content
  • multimedia
  • data sets
  • spatio temporal
  • machine learning
  • key frames
  • video clips
  • dialogue system