Sign in

Improving Zero-shot Generalization and Robustness of Multi-modal Models.

Yunhao GeJie RenYuxiao WangAndrew GallagherMing-Hsuan YangLaurent IttiHartwig AdamBalaji LakshminarayananJiaping Zhao
Published in: CoRR (2022)
Keyphrases
  • multi modal
  • audio visual
  • multi modality
  • high dimensional
  • cross modal
  • image annotation
  • humanoid robot
  • multimedia data
  • semantic concepts