skip to main content
10.1145/3394171.3414446acmconferencesArticle/Chapter ViewAbstractPublication PagesmmConference Proceedingsconference-collections
abstract

Fashionist: Personalising Outfit Recommendation for Cold-Start Scenarios

Published: 12 October 2020 Publication History

Abstract

With the proliferation of the online fashion industry, there have been increased efforts towards building cutting-edge solutions for personalising fashion recommendation. Despite this, the technology is still limited by its poor performance on new entities, i.e. the cold-start problem. We attempt to address the cold-start problem for new users, by leveraging a novel visual preference modelling approach on a small set of input images. Additionally, we describe our proposed strategy to incorporate the modelled preference in occasion-oriented outfit recommendation. Finally, we propose Fashionist: a real-time web application to demonstrate our approach enabling personalised and diverse outfit recommendation for cold-start scenarios. Check out https://youtu.be/kuKgPCkoPy0 for demonstration.

Supplementary Material

MP4 File (3394171.3414446.mp4)
Today, E-commerce for fashion is booming, but consumers still face issues while selecting fashion outfits that are appropriate in context and suit their liking. Various approaches have been adopted to personalise outfit recommendation. However, most of these works fail to address the cold-start problem. Addressing this problem is not only relevant to new users but also for users who prefer to experience the recommendation service in a "guest mode". We attempt to address this problem for new users, by leveraging a novel visual preference modelling approach on a small set of input images. For the same, we built Fashionist: a web-based application enabling personalised outfit recommendation for new users. In this application, users have to select their gender, upload a set of 10 images representing their fashion tastes, select the occasion and Voila! Top 10 occasion relevant outfits recommended, incorporating the users' preference. Finally, We demonstrate it's working and explain the concept behind it.

References

[1]
Anil Chaturvedi, Paul E Green, and J Douglas Caroll. 2001. K-modes clustering. Journal of classification, Vol. 18, 1 (2001), 35--55.
[2]
Wen Chen, Pipei Huang, Jiaming Xu, Xin Guo, Cheng Guo, Fei Sun, Chao Li, Andreas Pfadler, Huan Zhao, and Binqiang Zhao. 2019 b. POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, Anchorage AK USA, 2662--2670. https://doi.org/10.1145/3292500.3330652
[3]
Xu Chen, Hanxiong Chen, Hongteng Xu, Yongfeng Zhang, Yixin Cao, Zheng Qin, and Hongyuan Zha. 2019 a. Personalized Fashion Recommendation with Visual Explanations based on Multimodal Attention Network: Towards Visually Explainable Recommendation. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, Paris France, 765--774. https://doi.org/10.1145/3331184.3331254
[4]
Xintong Han, Zuxuan Wu, Yu-Gang Jiang, and Larry S. Davis. 2017. Learning Fashion Compatibility with Bidirectional LSTMs. In Proceedings of the 2017 ACM on Multimedia Conference - MM '17. ACM Press, Mountain View, California, USA, 1078--1086. https://doi.org/10.1145/3123266.3123394
[5]
Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv:1704.04861 [cs] (April 2017). http://arxiv.org/abs/1704.04861 arXiv: 1704.04861.
[6]
Yang Hu, Xi Yi, and Larry S. Davis. 2015. Collaborative Fashion Recommendation: A Functional Tensor Factorization Approach. In Proceedings of the 23rd ACM international conference on Multimedia - MM '15. ACM Press, Brisbane, Australia, 129--138. https://doi.org/10.1145/2733373.2806239
[7]
Blerina Lika, Kostas Kolomvatsos, and Stathes Hadjiefthymiades. 2014. Facing the cold start problem in recommender systems. Expert Systems with Applications, Vol. 41, 4 (March 2014), 2065--2073. https://doi.org/10.1016/j.eswa.2013.09.005
[8]
Si Liu, Jiashi Feng, Zheng Song, Tianzhu Zhang, Hanqing Lu, Changsheng Xu, and Shuicheng Yan. 2012. Hi, magic closet, tell me what to wear!. In Proceedings of the 20th ACM international conference on Multimedia - MM '12. ACM Press, Nara, Japan, 619. https://doi.org/10.1145/2393347.2393433
[9]
Ziwei Liu, Ping Luo, Shi Qiu, Xiaogang Wang, and Xiaoou Tang. 2016. DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Las Vegas, NV, USA, 1096--1104. https://doi.org/10.1109/CVPR.2016.124
[10]
Yunshan Ma, Xun Yang, Lizi Liao, Yixin Cao, and Tat-Seng Chua. 2019. Who, Where, and What to Wear?: Extracting Fashion Knowledge from Social Media. In Proceedings of the 27th ACM International Conference on Multimedia. ACM, Nice France, 257--265. https://doi.org/10.1145/3343031.3350889
[11]
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2016. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arXiv:1506.01497 [cs] (Jan. 2016). http://arxiv.org/abs/1506.01497 arXiv: 1506.01497.
[12]
Dikshant Sagar, Jatin Garg, Prarthana Kansal, Sejal Bhalla, Rajiv Ratn Shah, and Yi Yu. 2020. PAI-BPR: Personalized Outfit Recommendation Scheme with Attribute-wise Interpretability. arXiv:2008.01780 [cs] (Aug. 2020). http://arxiv.org/abs/2008.01780 arXiv: 2008.01780.
[13]
S.Aranganayagi and K.Thangavel. 2009. Improved K-Modes For Categorical Clustering Using Weighted Dissimilarity Measure. (March 2009). https://doi.org/10.5281/ZENODO.1070405 Publisher: Zenodo.
[14]
Xuemeng Song, Fuli Feng, Jinhuan Liu, Zekun Li, Liqiang Nie, and Jun Ma. 2017. NeuroStylist: Neural Compatibility Modeling for Clothing Matching. In Proceedings of the 2017 ACM on Multimedia Conference - MM '17. ACM Press, Mountain View, California, USA, 753--761. https://doi.org/10.1145/3123266.3123314
[15]
Dhruv Verma, Kshitij Gulati, and Rajiv Ratn Shah. 2020. Addressing the Cold-Start Problem in Outfit Recommendation Using Visual Preference Modelling. arXiv:2008.01437 [cs] (Aug. 2020). http://arxiv.org/abs/2008.01437 arXiv: 2008.01437.
[16]
Ruiping Yin, Kan Li, Jie Lu, and Guangquan Zhang. 2019. Enhancing Fashion Recommendation with Visual Compatibility Relationship. In The World Wide Web Conference on - WWW '19. ACM Press, San Francisco, CA, USA, 3434--3440. https://doi.org/10.1145/3308558.3313739
[17]
Yu Zhang and Qiang Yang. 2018. A Survey on Multi-Task Learning. arXiv:1707.08114 [cs] (July 2018). http://arxiv.org/abs/1707.08114 arXiv: 1707.08114.
[18]
Shuai Zheng, Fan Yang, M. Hadi Kiapour, and Robinson Piramuthu. 2019. ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotations. arXiv:1807.01394 [cs] (April 2019). http://arxiv.org/abs/1807.01394 arXiv: 1807.01394.

Cited By

View all
  • (2023)Computational Technologies for Fashion Recommendation: A SurveyACM Computing Surveys10.1145/362710056:5(1-45)Online publication date: 25-Nov-2023
  • (2022)DeepProfile: Accurate Under-the-Clothes Body Profile EstimationApplied Sciences10.3390/app1204222012:4(2220)Online publication date: 21-Feb-2022
  • (2022)Deep Learning Approaches for Fashion Knowledge Extraction From Social Media: A ReviewIEEE Access10.1109/ACCESS.2021.313789310(1545-1576)Online publication date: 2022
  • Show More Cited By

Index Terms

  1. Fashionist: Personalising Outfit Recommendation for Cold-Start Scenarios

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    MM '20: Proceedings of the 28th ACM International Conference on Multimedia
    October 2020
    4889 pages
    ISBN:9781450379885
    DOI:10.1145/3394171
    Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 12 October 2020

    Check for updates

    Author Tags

    1. cold-start problem
    2. fashion concept prediction
    3. multi-task learning
    4. personalised outfit recommendation

    Qualifiers

    • Abstract

    Conference

    MM '20
    Sponsor:

    Acceptance Rates

    Overall Acceptance Rate 2,145 of 8,556 submissions, 25%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)31
    • Downloads (Last 6 weeks)2
    Reflects downloads up to 18 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2023)Computational Technologies for Fashion Recommendation: A SurveyACM Computing Surveys10.1145/362710056:5(1-45)Online publication date: 25-Nov-2023
    • (2022)DeepProfile: Accurate Under-the-Clothes Body Profile EstimationApplied Sciences10.3390/app1204222012:4(2220)Online publication date: 21-Feb-2022
    • (2022)Deep Learning Approaches for Fashion Knowledge Extraction From Social Media: A ReviewIEEE Access10.1109/ACCESS.2021.313789310(1545-1576)Online publication date: 2022
    • (2022)Personalized Fashion Recommendation Using Pairwise AttentionMultiMedia Modeling10.1007/978-3-030-98355-0_19(218-229)Online publication date: 15-Mar-2022

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media