SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference.

Feng Wang Jieru Mei Alan L. Yuille

Published in: CoRR (2023)

Keyphrases

programming language
computer vision
vision system
visual attention
real time
probabilistic inference
visual field
natural language
image processing
bayesian networks
inference engine
high level vision
visual perception
artificial intelligence
language learning
expert systems
object recognition
neural network