Combining zero-padding with ROI pooling allows batch training on full-resolution photos, and adding a one-hot theme embedding improves aesthetic distribution prediction on AVA and Photo.net.
Ava: A large- scale database for aesthetic visual analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Theme-Aware Aesthetic Distribution Prediction With Full-Resolution Photographs
Combining zero-padding with ROI pooling allows batch training on full-resolution photos, and adding a one-hot theme embedding improves aesthetic distribution prediction on AVA and Photo.net.