Sign in

Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks.

Jiasen LuChristopher ClarkRowan ZellersRoozbeh MottaghiAniruddha Kembhavi
Published in: CoRR (2022)
Keyphrases
  • multi modal
  • unified model
  • multi modality
  • cross modal
  • high dimensional
  • computer vision
  • semantic concepts
  • fusing multiple
  • image annotation
  • similarity measure
  • video sequences
  • video search