Login / Signup

Scene-robust Natural Language Video Localization via Learning Domain-invariant Representations.

Zehan WangYang ZhaoHaifeng HuangYan XiaZhou Zhao
Published in: ACL (Findings) (2023)
Keyphrases
  • natural language
  • video sequences
  • invariant representations
  • machine learning
  • viewpoint
  • computer vision
  • three dimensional
  • moving objects
  • video data