Login / Signup

Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching.

Bofeng WuGuocheng NiuJun YuXinyan XiaoJian ZhangHua Wu
Published in: IJCAI (2021)
Keyphrases
  • weakly supervised
  • cross modal
  • video sequences
  • visual data
  • knowledge base
  • multimedia
  • multi modal
  • video data
  • superpixels
  • topic models
  • object detectors