AesRec: A Dataset for Aesthetics-Aligned Clothing Outfit Recommendation

2026-02-03

AI Summary

This work addresses the limitation of existing fashion recommendation methods, which often lack explicit aesthetic modeling and struggle to balance personalization with aesthetic guidance. To bridge this gap, the authors introduce AesRec, a novel dataset featuring a multidimensional aesthetic annotation framework grounded in professional fashion standards, encompassing both individual garments and full outfits. Leveraging vision-language models, the framework enables large-scale, scalable aesthetic scoring, complemented by human validation to ensure alignment between human and machine judgments. Experimental results demonstrate that integrating this quantified aesthetic representation into recommendation models significantly enhances system performance in aligning with both user preferences and aesthetic principles.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Humans and AI: Learning Human Values and Preferences
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Clothing recommendation extends beyond merely generating personalized outfits; it serves as a crucial medium for aesthetic guidance. However, existing methods predominantly rely on user-item-outfit interaction behaviors while overlooking explicit representations of clothing aesthetics. To bridge this gap, we present the AesRec benchmark dataset featuring systematic quantitative aesthetic annotations, thereby enabling the development of aesthetics-aligned recommendation systems. Grounded in professional apparel quality standards and fashion aesthetic principles, we define a multidimensional set of indicators. At the item level, six dimensions are independently assessed: silhouette, chromaticity, materiality, craftsmanship, wearability, and item-level impression. Transitioning to the outfit level, the evaluation retains the first five core attributes while introducing stylistic synergy, visual harmony, and outfit-level impression as distinct metrics to capture the collective aesthetic impact. Given the increasing human-like proficiency of Vision-Language Models in multimodal understanding and interaction, we leverage them for large-scale aesthetic scoring. We conduct rigorous human-machine consistency validation on a fashion dataset, confirming the reliability of the generated ratings. Experimental results based on AesRec further demonstrate that integrating quantified aesthetic information into clothing recommendation models can provide aesthetic guidance for users while fulfilling their personalized requirements.

Problem

• clothing recommendation
• aesthetics
• outfit recommendation
• fashion aesthetics
• aesthetic alignment

Innovation

• aesthetic-aligned recommendation
• multidimensional aesthetic annotation
• vision-language models
• outfit recommendation
• human-machine consistency