CORE: Color Regression for Multiple Colors Fashion Garments

by   Alexandre Ramé, et al.

Among all fashion attributes, color is challenging to detect due to its subjective perception. Existing classification approaches can not go beyond the predefined list of discrete color names. In this paper, we argue that color detection is a regression problem. Thus, we propose a new architecture, based on attention modules and in two-stages. The first stage corrects the image illumination while detecting the main discrete color name. The second stage combines a colorname-attention (dependent of the detected color) with an object-attention (dependent of the clothing category) and finally weights a spatial pooling over the image pixels' RGB values. We further expand our work for multiple colors garments. We collect a dataset where each fashion item is labeled with a continuous color palette: we empirically show the benefits of our approach.


Color Counting for Fashion, Art, and Design

Color modelling and extraction is an important topic in fashion, art, an...

Darks and Stripes: Effects of Clothing on Weight Perception

In many societies, appearing slim is considered attractive. The fashion ...

AI Décor

Confused about renovating your space? Choosing the perfect color for you...

Jointly Optimizing Color Rendition and In-Camera Backgrounds in an RGB Virtual Production Stage

While the LED panels used in virtual production systems can display vibr...

Artificial Color Constancy via GoogLeNet with Angular Loss Function

Color Constancy is the ability of the human visual system to perceive co...

TransCC: Transformer-based Multiple Illuminant Color Constancy Using Multitask Learning

Multi-illuminant color constancy is a challenging problem with only a fe...

Weakly Supervised Domain-Specific Color Naming Based on Attention

The majority of existing color naming methods focuses on the eleven basi...

Please sign up or login with your details

Forgot password? Click here to reset