VLMAE: Vision-Language Masked Autoencoder.

Sunan He Taian Guo Tao Dai Ruizhi Qiao Chen Wu Xiujun Shu Bo Ren

Published in: CoRR (2022)

Keyphrases

programming language
computer vision
vision system
natural language
multi agent systems
image processing
language learning
computational linguistics
general purpose
logic programs
real world
context dependent
conceptual graphs
target language
linguistic knowledge
operational semantics
english language