Addressing the Cold-Start Problem in Outfit Recommendation Using Visual Preference Modelling

被引:9
|
作者
Verma, Dhruv [1 ]
Gulati, Kshitij [1 ]
Shah, Rajiv Ratn [1 ]
机构
[1] Indraprastha Inst Informat Technol, Delhi, India
关键词
personalised outfit recommendation; cold-start problem; visual preference modelling; feature-weighted clustering;
D O I
10.1109/BigMM50055.2020.00043
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
With the global transformation of the fashion industry and a rise in the demand for fashion items worldwide, the need for an effectual fashion recommendation has never been more. Despite various cutting-edge solutions proposed in the past for personalising fashion recommendation, the technology is still limited by its poor performance on new entities, i.e. the cold-start problem. In this paper, 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. We demonstrate the use of our approach with feature-weighted clustering to personalise occasion-oriented outfit recommendation. Quantitatively, our results show that the proposed visual preference modelling approach outperforms state of the art in terms of clothing attribute prediction. Qualitatively, through a pilot study, we demonstrate the efficacy of our system to provide diverse and personalised recommendations in cold-start scenarios.
引用
收藏
页码:251 / 256
页数:6
相关论文
共 50 条
  • [41] Alleviating Cold-Start Problem by Using Implicit Feedback
    Zhang, Lei
    Meng, Xiang-Wu
    Chen, Jun-Liang
    Xiong, Si-Cheng
    Duan, Kull
    [J]. ADVANCED DATA MINING AND APPLICATIONS, PROCEEDINGS, 2009, 5678 : 763 - 771
  • [42] Addressing the Item Cold-Start Problem by Attribute-Driven Active Learning
    Zhu, Yu
    Lin, Jinghao
    He, Shibi
    Wang, Beidou
    Guan, Ziyu
    Liu, Haifeng
    Cai, Deng
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2020, 32 (04) : 631 - 644
  • [43] CoMeta: Enhancing Meta Embeddings with Collaborative Information in Cold-Start Problem of Recommendation
    Hu, Haonan
    Rong, Dazhong
    Chen, Jianhai
    He, Qinming
    Liu, Zhenguang
    [J]. KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT III, KSEM 2023, 2023, 14119 : 213 - 225
  • [44] Eliminating Cold-Start Problem of Music Recommendation through SOM Based Sampling
    Liu, Ning-Han
    Chiang, Cheng-Yu
    Hsu, Hsiang-Ming
    [J]. ADVANCES IN MECHATRONICS AND CONTROL ENGINEERING, PTS 1-3, 2013, 278-280 : 1119 - 1123
  • [45] Ice-Breaking: Mitigating Cold-Start Recommendation Problem by Rating Comparison
    Xu, Jingwei
    Yao, Yuan
    Tong, Hanghang
    Tao, Xianping
    Lu, Jian
    [J]. PROCEEDINGS OF THE TWENTY-FOURTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI), 2015, : 3981 - 3987
  • [46] SVD++ AND CLUSTERING APPROACHES TO ALLEVIATING THE COLD-START PROBLEM FOR RECOMMENDATION SYSTEMS
    Al-Sabaawi, Ali Mohsin Ahmed
    Karacan, Hacer
    Yenice, Yusuf Erkan
    [J]. INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2021, 17 (02): : 383 - 396
  • [47] Addressing Cold-Start in App Recommendation: Latent User Models Constructed from Twitter Followers
    Lin, Jovian
    Sugiyama, Kazunari
    Kan, Min-Yen
    Chua, Tat-Seng
    [J]. SIGIR'13: THE PROCEEDINGS OF THE 36TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH & DEVELOPMENT IN INFORMATION RETRIEVAL, 2013, : 283 - 292
  • [48] Using semantic web to reduce the cold-start problems in recommendation systems
    Nouali, Omar
    Belloui, Amokrane
    [J]. 2009 SECOND INTERNATIONAL CONFERENCE ON THE APPLICATIONS OF DIGITAL INFORMATION AND WEB TECHNOLOGIES (ICADIWT 2009), 2009, : 525 - 530
  • [49] Towards Addressing Item Cold-Start Problem in Collaborative Filtering by Embedding Agglomerative Clustering and FP-Growth into the Recommendation System
    Kannout, Eyad
    Grodzki, Michal
    Grzegorowski, Marek
    [J]. COMPUTER SCIENCE AND INFORMATION SYSTEMS, 2023, 20 (04) : 1343 - 1366
  • [50] Relation-propagation meta-learning on an explicit preference graph for cold-start recommendation
    Liu, Huiting
    Wang, Lei
    Li, Peipei
    Qian, Cheng
    Zhao, Peng
    Wu, Xindong
    [J]. KNOWLEDGE-BASED SYSTEMS, 2023, 272