Unifying Vision-and-Language Tasks via Text Generation.

Jaemin Cho Jie Lei Hao Tan Mohit Bansal

Published in: ICML (2021)

Keyphrases

text generation
natural language generation
natural language
visually guided
computer vision
vision system
image processing
theorem prover
neural network
real time
robotic systems
multiple tasks
human vision
conceptual graphs
multi task
information extraction
machine learning
databases