用专业知识指导多步穿搭推荐，让个性化搭配更透明可靠。
StePO-Rec: Towards Personalized Outfit Styling Assistant via Knowledge-Guided Multi-Step Reasoning
- 基于三层专业知识库，构建可解释的穿搭推理框架
- 在IQON数据集上召回率提升28%，MAP提高32.8%
- 适合需要可解释性与专业度的智能穿搭系统开发者
生成式AI为时尚智能带来新机遇，突破传统推荐系统透明度低、难融合专家知识的局限，释放个性化穿搭潜力。为此，我们提出PAFA（原则感知时尚知识库），将专业穿搭知识组织为元数据、领域原则和语义关系三个层次。基于PAFA，我们开发了StePO-Rec——一种基于知识的多步穿搭推荐方法。该方法采用场景-维度-属性框架，通过递归树构建对齐专业原则与用户偏好。此外，引入偏好趋势重排序机制，在顺应潮流的同时保持用户原有风格一致性。在广泛使用的个性化穿搭数据集IQON上的实验表明，Recall@1提升28%，MAP提升32.8%。案例研究进一步验证了推荐结果在可解释性、可追溯性、可靠性方面的显著改善，并实现专家知识与个性化推荐的无缝融合。
原文摘要 · Abstract (English)
Advancements in Generative AI offers new opportunities for FashionAI, surpassing traditional recommendation systems that often lack transparency and struggle to integrate expert knowledge, leaving the potential for personalized fashion styling remain untapped. To address these challenges, we present PAFA (Principle-Aware Fashion), a multi-granular knowledge base that organizes professional styling expertise into three levels of metadata, domain principles, and semantic relationships. Using PAFA, we develop StePO-Rec, a knowledge-guided method for multi-step outfit recommendation. StePO-Rec provides structured suggestions using a scenario-dimension-attribute framework, employing recursive tree construction to align recommendations with both professional principles and individual preferences. A preference-trend re-ranking system further adapts to fashion trends while maintaining the consistency of the user's original style. Experiments on the widely used personalized outfit dataset IQON show a 28% increase in Recall@1 and 32.8% in MAP. Furthermore, case studies highlight improved explainability, traceability, result reliability, and the seamless integration of expertise and personalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。