CLIP4VideoCap: Rethinking Clip for Video Captioning with Multiscale Temporal Fusion and Commonsense Knowledge

Document Details

Document Type
Pub Defense Publication
Publication Date
Jun 04, 2023
Source ID
10.1109/icassp49357.2023.10097128

Entities

People

  • Diana Marculescu
  • Liang Feng
  • Tanvir Mahmud
  • Yaling Qing

Organizations

  • Office of Naval Research
  • University of Texas at Austin