Personalized Fashion Recommendation from Personal Social Media Data: An Item-to-Set Metric Learning Approach

被引:9
作者
Zheng, Haitian [1 ]
Wu, Kefei [1 ]
Park, Jong-Hwi [1 ]
Zhu, Wei [1 ]
Luo, Jiebo [1 ]
机构
[1] Univ Rochester, Dept Comp Sci, Rochester, NY 14627 USA
来源
2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA) | 2021年
关键词
Fashion recommendation; Recommendation system; Social Media; Metric learning; CLOTHING RETRIEVAL;
D O I
10.1109/BigData52589.2021.9671563
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
With the growth of online shopping for fashion products, accurate fashion recommendation has become a critical problem. Meanwhile, social networks provide an open and new data source for personalized fashion analysis. In this work, we study the problem of personalized fashion recommendation from social media data, i.e. recommending new outfits to social media users that fit their fashion preferences. To this end, we present an item-to-set metric learning framework that learns to compute the similarity between a set of historical fashion items of a user to a new fashion item. To extract features from multi-modal street-view fashion items, we propose an embedding module that performs multi-modality feature extraction and cross-modality gated fusion. To validate the effectiveness of our approach, we collect a real-world social media dataset. Extensive experiments on the collected dataset show the superior performance of our proposed approach.
引用
收藏
页码:5014 / 5023
页数:10
相关论文
共 46 条
[1]   Learning Attribute Representations with Localization for Flexible Fashion Search [J].
Ak, Kenan E. ;
Kassim, Ashraf A. ;
Lim, Joo Hwee ;
Tham, Jo Yew .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :7708-7717
[2]   Product Characterisation towards Personalisation Learning Attributes from Unstructured Data to Recommend Fashion Products [J].
Cardoso, Angelo ;
Daolio, Fabio ;
Vargas, Saul .
KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, :80-89
[3]   Describing Clothing by Semantic Attributes [J].
Chen, Huizhong ;
Gallagher, Andrew ;
Girod, Bernd .
COMPUTER VISION - ECCV 2012, PT III, 2012, 7574 :609-623
[4]  
Chen Q, 2015, PROC CVPR IEEE, P5315, DOI 10.1109/CVPR.2015.7299169
[5]   Towards Unified Human Parsing and Pose Estimation [J].
Dong, Jian ;
Chen, Qiang ;
Shen, Xiaohui ;
Yang, Jianchao ;
Yan, Shuicheng .
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :843-850
[6]   Instance-Level Human Parsing via Part Grouping Network [J].
Gong, Ke ;
Liang, Xiaodan ;
Li, Yicheng ;
Chen, Yimin ;
Yang, Ming ;
Lin, Liang .
COMPUTER VISION - ECCV 2018, PT IV, 2018, 11208 :805-822
[7]  
Hadsell R., 2006, PROC IEEE C COMPUT V, P1742, DOI [10.1109/CVPR.2006.100, DOI 10.1109/CVPR.2006.100]
[8]   Learning Fashion Compatibility with Bidirectional LSTMs [J].
Han, Xintong ;
Wu, Zuxuan ;
Jiang, Yu-Gang ;
Davis, Larry S. .
PROCEEDINGS OF THE 2017 ACM MULTIMEDIA CONFERENCE (MM'17), 2017, :1078-1086
[9]   Creating Capsule Wardrobes from Fashion Images [J].
Hsiao, Wei-Lin ;
Grauman, Kristen .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :7161-7170
[10]   Collaborative Fashion Recommendation: A Functional Tensor Factorization Approach [J].
Hu, Yang ;
Yi, Xi ;
Davis, Larry S. .
MM'15: PROCEEDINGS OF THE 2015 ACM MULTIMEDIA CONFERENCE, 2015, :129-138