Pith. sign in

For training, the input image size is fixed at600× 600, and random crops of size 512× 512 are applied to the image

RESULTS Training, Implementation Details: We split the dataset of 180 images into training, validation, test sets in an 80%, 10%, 10% setting

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.MM 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

ColorNet -- Estimating Colorfulness in Natural Images

cs.MM · 2019-08-22 · conditional · novelty 6.0

ColorNet, a CNN fine-tuned on a newly aligned 180-image subjective dataset, reports Pearson correlation 0.937 with human colorfulness ratings, beating classical colorfulness metrics.

citing papers explorer

Showing 1 of 1 citing paper.

  • ColorNet -- Estimating Colorfulness in Natural Images cs.MM · 2019-08-22 · conditional · none · ref 8

    ColorNet, a CNN fine-tuned on a newly aligned 180-image subjective dataset, reports Pearson correlation 0.937 with human colorfulness ratings, beating classical colorfulness metrics.