Login / Signup

GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery.

Enguang WangZhimao PengZhengyuan XieXialei LiuMing-Ming Cheng
Published in: CoRR (2024)
Keyphrases
  • multi modal
  • multi modality
  • audio visual
  • cross modal
  • image annotation
  • semantic concepts
  • high dimensional
  • video clips
  • humanoid robot
  • machine learning
  • object recognition
  • magnetic resonance images
  • video search