How Good Is Aesthetic Ability of a Fashion Model?

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.

[1]  Ahmad Kalhor,et al.  Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industry , 2021, ArXiv.

[2]  Ruomei Wang,et al.  Learning Outfit Compatibility with Graph Attention Network and Visual-Semantic Embedding , 2021, 2021 IEEE International Conference on Multimedia and Expo (ICME).

[3]  Yang Hu,et al.  Personalized Outfit Recommendation with Learnable Anchors , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Xingxing Zou,et al.  fAshIon after fashion: A Report of AI in Fashion , 2021, ArXiv.

[5]  Tao Mei,et al.  Learning the Compositional Visual Coherence for Complementary Recommendations , 2020, IJCAI.

[6]  Dahua Lin,et al.  Regularizing Reasons for Outfit Evaluation with Gradient Penalty , 2020, ArXiv.

[7]  Kate Saenko,et al.  Learning Similarity Conditions Without Explicit Supervision , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[8]  Zhi Lu,et al.  Learning Binary Code for Personalized Fashion Recommendation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Xin Guo,et al.  POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion , 2019, KDD.

[10]  Luisa F. Polanía,et al.  Learning Fashion Compatibility Across Apparel Categories for Outfit Recommendation , 2019, 2019 IEEE International Conference on Image Processing (ICIP).

[11]  Le Wu,et al.  Explainable Fashion Recommendation: A Semantic Attribute Region Guided Approach , 2019, IJCAI.

[12]  Xiaoyu Zhang,et al.  Dressing as a Whole: Outfit Compatibility Learning Based on Node-wise Graph Neural Networks , 2019, WWW.

[13]  David Vázquez,et al.  Context-Aware Visual Compatibility Prediction , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Meng Wang,et al.  TransNFCM: Translation-Based Neural Fashion Compatibility Modeling , 2018, AAAI.

[15]  Zhaochun Ren,et al.  Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation , 2018, IEEE Transactions on Knowledge and Data Engineering.

[16]  David A. Forsyth,et al.  Learning Type-Aware Embeddings for Fashion Compatibility , 2018, ECCV.

[17]  Kristen Grauman,et al.  Creating Capsule Wardrobes from Fashion Images , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Lizhi Cai,et al.  Fashion coordinates recommendation based on user behavior and visual clothing style , 2017, ICCIP.

[19]  Liqiang Nie,et al.  NeuroStylist: Neural Compatibility Modeling for Clothing Matching , 2017, ACM Multimedia.

[20]  Yu-Gang Jiang,et al.  Learning Fashion Compatibility with Bidirectional LSTMs , 2017, ACM Multimedia.

[21]  Tegan Maharaj,et al.  A Dataset and Exploration of Models for Understanding Video Data through Fill-in-the-Blank Question-Answering , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Jiebo Luo,et al.  Mining Fashion Outfit Composition Using an End-to-End Deep Learning Approach on Set Data , 2016, IEEE Transactions on Multimedia.

[23]  Licheng Yu,et al.  Visual Madlibs: Fill in the Blank Description Generation and Question Answering , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[24]  Ernani Viriato de Melo,et al.  Content-Based Filtering Enhanced by Human Visual Attention Applied to Clothing Recommendation , 2015, 2015 IEEE 27th International Conference on Tools with Artificial Intelligence (ICTAI).

[25]  Larry S. Davis,et al.  Collaborative Fashion Recommendation: A Functional Tensor Factorization Approach , 2015, ACM Multimedia.

[26]  Serge J. Belongie,et al.  Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[27]  Anton van den Hengel,et al.  Image-Based Recommendations on Styles and Substitutes , 2015, SIGIR.

[28]  Kristen Grauman,et al.  Fine-Grained Visual Comparisons with Local Learning , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  V. Jagadeesh,et al.  Large scale visual recommendations from street fashion images , 2014, KDD.

[30]  Tomoharu Iwata,et al.  Fashion Coordinates Recommender System Using Photographs from Fashion Magazines , 2011, IJCAI.

[31]  Joanne Entwistle,et al.  The Aesthetic Economy of Fashion: Markets and Value in Clothing and Modelling , 2009 .

[32]  Henry Lieberman,et al.  What am I gonna wear?: scenario-oriented recommendation , 2007, IUI '07.

[33]  Ling-Yu Duan,et al.  $A^3$-FKG: Attentive Attribute-Aware Fashion Knowledge Graph for Outfit Preference Prediction , 2022, IEEE Transactions on Multimedia.

[34]  Molly Eckman,et al.  Aesthetic Aspects of the Consumption of Fashion Design: the Conceptual and Empirical Challenge , 1995 .

[35]  Ruth Estella Hawthorne.  Aspects of design preference in clothing : aesthetic, motivation, and knowledge / , 1967 .

[36]  Open Research , 2022 .