\n \n \n \n \n \n \n
Figure 1: Suggesting names for a color and finding colors that fit a description.
\nThis work learns a shared representation of colors and their names from sparse, uneven crowdsourced observations. Text and RGB encoders align matching examples while negative samples help distinguish unsuitable associations. A separate generator predicts RGB values from text, and joint training supports both naming a supplied color and producing colors from a description. Evaluation on the XKCD dataset reports improved recommendations and lower perceptual error compared with prior approaches, with 71.26% top-ten naming accuracy and a CIELAB error of 26.61 for generated colors.
\n\n \n \n \n
\nFigure 2: RGB samples associated with three different color terms.
\n\n \n \n \n
\nFigure 3: Encoders, training objectives, and RGB prediction in the proposed system.
\n\n \n \n \n
\nTable 1: Effects of removing individual model components.
\n\n \n \n 
\n \n
Table 2: Naming accuracy, perceptual error, and query time on held-out data.
\n\n \n \n \n
\nFigure 4: Example naming suggestions and recommended color swatches.
","frontmatter":{"title":"Contrastive Learning for Large-scale Color-Name Dataset: Tackling Sparsity with Negative Sampling","year":"2026","authors":["Kecheng Lu","Yue He","Yunhai Wang"],"publication":"The ACM SIGCHI Conference on Human Factors in Computing Systems (CHI 2026), 2026"}}},"pageContext":{"id":"ac6ef0b6-22e9-5926-8220-46df634932c7"}},"staticQueryHashes":["63159454"]}