Login / Signup

Multimodal feature fusion based on object relation for video captioning.

Zhiwen YanYing ChenJinlong SongJia Zhu
Published in: CAAI Trans. Intell. Technol. (2023)
Keyphrases
  • feature fusion
  • feature extraction
  • multiple features
  • video sequences
  • multi modal
  • video data
  • d objects
  • video frames
  • data reduction
  • canonical correlation analysis