• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning.

Mandela PatrickPo-Yao HuangIshan MisraFlorian MetzeAndrea VedaldiYuki M. AsanoJoão F. Henriques
Published in: ICCV (2021)
Keyphrases
  • space time
  • video representation
  • spatio temporal
  • cross modal
  • spatial and temporal
  • video sequences
  • object recognition
  • motion patterns
  • machine learning
  • computer vision
  • multimedia
  • video content
  • human actions