Login / Signup

Self-Supervised Video Representation Learning via Capturing Semantic Changes Indicated by Saccades.

Qiuxia LaiAiling ZengYe WangLihong CaoYu LiQiang Xu
Published in: IEEE Trans. Circuits Syst. Video Technol. (2024)
Keyphrases
  • high level
  • eye movements
  • video representation
  • spatio temporal
  • image database
  • em algorithm
  • human computer interaction