Login / Signup

FM-OV3D: Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection.

Dongmei ZhangChang LiRay ZhangShenghao XieWei XueXiaodong XieShanghang Zhang
Published in: CoRR (2023)
Keyphrases
  • cross modal
  • multi modal
  • domain knowledge
  • knowledge base
  • object detection
  • perceptual information
  • information retrieval
  • visual data
  • visual recognition
  • e learning
  • co occurrence
  • visual similarity