Login / Signup
VisualGPT: Data-efficient Image Captioning by Balancing Visual Input and Linguistic Knowledge from Pretraining.
Jun Chen
Han Guo
Kai Yi
Boyang Li
Mohamed Elhoseiny
Published in:
CoRR (2021)
Keyphrases
</>
image data
data analysis
linguistic knowledge
visual input
image features
input image
visual data
high level
similarity measure
image classification
high resolution
image content
visual information
multimedia data