{"title":"Visual Metaphor Construction for Image and Description of Fashion Goods","authors":"Dan Wang, Ryota Mibayashi, Hiroaki Ohshima","doi":"10.1109/IIAIAAI55812.2022.00040","DOIUrl":null,"url":null,"abstract":"In this study, we propose a method for constructing visual metaphors for fashion goods. The input of the proposed method consists of a product image and its product description. For example, for a red jacket with good stretch, the visual metaphor constructed by the proposed method will be \"leaping fire of youth\". For a pair of black high heels that can create an elegant temperament, the constructed visual metaphor will be \"beautiful slender swallows\". A visual metaphor is something that is similar in appearance to a fashion goods. Construction of visual metaphor will bring inspiration to poster design or any other form of propaganda. The process of the proposed method consists of two parts. First, we build a deep learning model to predict the similarity between fashion goods and metaphor on color and pattern, and obtain metaphor words based on the predicted similarity. After that, we use the obtained metaphor word and product description to generate rhetoric.","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IIAIAAI55812.2022.00040","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this study, we propose a method for constructing visual metaphors for fashion goods. The input of the proposed method consists of a product image and its product description. For example, for a red jacket with good stretch, the visual metaphor constructed by the proposed method will be "leaping fire of youth". For a pair of black high heels that can create an elegant temperament, the constructed visual metaphor will be "beautiful slender swallows". A visual metaphor is something that is similar in appearance to a fashion goods. Construction of visual metaphor will bring inspiration to poster design or any other form of propaganda. The process of the proposed method consists of two parts. First, we build a deep learning model to predict the similarity between fashion goods and metaphor on color and pattern, and obtain metaphor words based on the predicted similarity. After that, we use the obtained metaphor word and product description to generate rhetoric.