EventLens: Leveraging Event-Aware Pretraining and Cross-modal Linking Enhances Visual Commonsense Reasoning.

Mingjie Ma Zhihuan Yu Yichao Ma Guohui Li

Published in: CoRR (2024)

Keyphrases

cross modal
commonsense reasoning
multi modal
nonmonotonic reasoning
incomplete information
event calculus

multimedia retrieval
visual data
visual recognition
image retrieval
knowledge representation
perceptual information

multimedia databases
visual similarity
classical logic
autoepistemic logic
formal theory

visual information
logic programming
image classification
missing information
feature space