Login / Signup

Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-Modal Structured Representations.

Yufeng HuangJiji TangZhuo ChenRongsheng ZhangXinfeng ZhangWeijie ChenZeng ZhaoZhou ZhaoTangjie LvZhipeng HuWen Zhang
Published in: AAAI (2024)
Keyphrases
  • multi modal
  • structured representations
  • knowledge base
  • multi modality
  • video sequences
  • cross modal
  • random walk
  • high dimensional
  • uni modal
  • machine learning
  • information extraction
  • plan recognition
  • single modality