@pascalmettes : All vision-language models should have hyperbolic embeddings. Vision and language are incredibly hierarchical in nature! See below our latest work on hyperbolic vision-language models that exploit visual compositions through entailment: • TwiCopy

Pascal Mettes

@pascalmettes

+ Follow

Assistant Professor - University of Amsterdam | Hyperbolic deep learning

ID: 1240583910419050496

calendar_today19-03-2020 10:20:35

365 Tweet

1,1K Takipçi

683 Takip Edilen

Pascal Mettes

@pascalmettes

a year ago

All vision-language models should have hyperbolic embeddings. Vision and language are incredibly hierarchical in nature! See below our latest work on hyperbolic vision-language models that exploit visual compositions through entailment:

thumb_up_off_alt156

chat_bubble_outline2

repeat12

shareShare