Visual Commonsense in Pretrained Unimodal and Multimodal Models.

Chenyu Zhang Benjamin Van Durme Zhuowan Li Elias Stengel-Eskin

Published in: NAACL-HLT (2022)

Keyphrases

probabilistic model
database
low level
multi modal
statistical models
social networks
knowledge base
machine learning algorithms
experimental data
visual information
visual perception