DiCo: Disentangled Concept Representation for Text-to-image Person Re-identification
DiCo: 用于文本到图像人物重识别的解耦概念表示
机构 * organization= Department of Imaging Science, Graduate School of Advanced Imaging Science, Multimedia \& Film, Chung-Ang University , addressline= , city= Seoul , postcode= 06974 , state= , country= South Korea ; organization= Department of Metaverse Convergence, Graduate School of Advanced Imaging Science, Multimedia \& Film, Chung-Ang University , addressline= , city= Seoul , postcode= 06974 , state= , country= South Korea
专题命中 文生图 :text-to-image(title,abstract);分类 cs.CV
AI总结 DiCo通过解耦概念表示方法,提升文本到图像人物重识别的跨模态对齐和可解释性。