Learning Attribute Representations with Localization for Flexible Fashion Search

被引:82
作者
Ak, Kenan E. [1 ,2 ]
Kassim, Ashraf A. [1 ]
Lim, Joo Hwee [2 ]
Tham, Jo Yew [3 ]
机构
[1] Natl Univ Singapore, Singapore, Singapore
[2] ASTAR, Inst Infocomm Res, Singapore, Singapore
[3] ESP xMedia Pte Ltd, Singapore, Singapore
来源
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2018年
关键词
D O I
10.1109/CVPR.2018.00804
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper we investigate ways of conducting a detailed fashion search using query images and attributes. A credible fashion search platform should be able to (1) find images that share the same attributes as the query image, (2) allow users to manipulate certain attributes, e.g. replace collar attribute from round to v-neck, and (3) handle region-specific attribute manipulations, e.g. replacing the color attribute of the sleeve region without changing the color attribute of other regions. A key challenge to be addressed is that fashion products have multiple attributes and it is important for each of these attributes to have representative features. To address these challenges, we propose the FashionSearchNet which uses a weakly supervised localization method to extract regions of attributes. By doing so, unrelated features can be ignored thus improving the similarity learning. Also, FashionSearchNet incorporates a new procedure that enables region awareness to be able to handle region-specific requests. FashionSearchNet outperforms the most recent fashion search techniques and is shown to be able to carry out different search scenarios using the dynamic queries.
引用
收藏
页码:7708 / 7717
页数:10
相关论文
共 47 条
  • [11] CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1023/A:1022627411411
  • [12] Histograms of oriented gradients for human detection
    Dalal, N
    Triggs, B
    [J]. 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, : 886 - 893
  • [13] Image retrieval: Ideas, influences, and trends of the new age
    Datta, Ritendra
    Joshi, Dhiraj
    Li, Jia
    Wang, James Z.
    [J]. ACM COMPUTING SURVEYS, 2008, 40 (02)
  • [14] Multi-Task Curriculum Transfer Deep Learning of Clothing Attributes
    Dong, Qi
    Gong, Shaogang
    Zhu, Xiatian
    [J]. 2017 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2017), 2017, : 520 - 529
  • [15] Dress like a Star: Retrieving Fashion Products from Videos
    Garcia, Noa
    Vogiatzis, George
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017), 2017, : 2293 - 2299
  • [16] Fast R-CNN
    Girshick, Ross
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 1440 - 1448
  • [17] Deep Image Retrieval: Learning Global Representations for Image Search
    Gordo, Albert
    Almazan, Jon
    Revaud, Jerome
    Larlus, Diane
    [J]. COMPUTER VISION - ECCV 2016, PT VI, 2016, 9910 : 241 - 257
  • [18] Learning Fashion Compatibility with Bidirectional LSTMs
    Han, Xintong
    Wu, Zuxuan
    Jiang, Yu-Gang
    Davis, Larry S.
    [J]. PROCEEDINGS OF THE 2017 ACM MULTIMEDIA CONFERENCE (MM'17), 2017, : 1078 - 1086
  • [19] Automatic Spatially-aware Fashion Concept Discovery
    Han, Xintong
    Wu, Zuxuan
    Huang, Phoenix X.
    Zhang, Xiao
    Zhu, Menglong
    Li, Yuan
    Zhao, Yang
    Davis, Larry S.
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 1472 - 1480
  • [20] Deep Metric Learning Using Triplet Network
    Hoffer, Elad
    Ailon, Nir
    [J]. SIMILARITY-BASED PATTERN RECOGNITION, SIMBAD 2015, 2015, 9370 : 84 - 92