How Good Is Aesthetic Ability of a Fashion Model?
Xingxing Zou, Kaicheng Pang, Wen Zhang, Waikeung Wong
摘要
We introduce A100 (Aesthetic 100) to assess the aesthetic ability of the fashion compatibility models. To date, it is the first work to address the AI model's aesthetic ability with detailed characterization based on the professional fashion domain knowledge. A100 has several desirable characteristics: 1. Completeness. It covers all types of standards in the fashion aesthetic system through two tests, namely LAT (Liberalism Aesthetic Test) and AAT (Academicism Aesthetic Test); 2. Reliability. It is training data agnostic and consistent with major indicators. It provides a fair and objective judgment for model comparison. 3. Explainability. Better than all previous indicators, the A100 further identifies essential characteristics of fashion aesthetics, thus showing the model's performance on more fine-grained dimensions, such as Color, Balance, Material, etc. Experimental results prove the advance of the A100 in the aforementioned aspects. All data can be found at https://github.com/AemikaChow/AiDLab- fAshIon-Data.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and AccessoriesJunyao Hu, Zhongwei Cheng, Waikeung Wong, Xingxing ZouCVPR 2026 · 被引用 4 次
- FashionSAP: Symbols and Attributes Prompt for Fine-Grained Fashion Vision-Language Pre-TrainingYunpeng Han, Lisai Zhang, Qingcai Chen, Zhijian Chen 等CVPR 2023
它引用的顶会 Paper2
相关 Paper
- FiNet: Compatible and Diverse Fashion Image InpaintingXintong Han, Zuxuan Wu, Weilin Huang, Matthew R. Scott 等ICCV 2019 · 被引用 85 次
- Can Vision-Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset PerspectiveRuichuan An, Shizhao Sun, Danqing Huang, Mingxi Cheng 等ICLR 2026 · 被引用 6 次
- Deciphering Compatibility Relationships with Textual Descriptions via Extraction and ExplanationYu Wang, Zexue He, Zhankui He, Hao Xu 等AAAI 2024 · 被引用 6 次
- FANCY: Human-centered, Deep Learning-based Framework for Fashion Style AnalysisYoungseung Jeon, Seungwan Jin, Kyungsik HanWWW 2021 · 被引用 25 次
- StyleMe: Towards Intelligent Fashion Generation with Designer StyleDi Wu, Zhiwang Yu, Nan Ma, Jianan Jiang 等CHI 2023 · 被引用 52 次
