Fashion Landmark-Driven Feature Exploitation Network for Clothing Recognition 


Vol. 45,  No. 5, pp. 801-804, May  2020
10.7840/kics.2020.45.5.801


PDF
  Abstract

Due to non-rigid deformations, it is hard to apply algorithms on fashion images. To overcome this problem and imporve performances of Fabric and Part attributes, in this paper, we propose a clothing recognition method with fashion landmark features. The proposed method exploits contextual features of a fashion item, which is generated in fashion landmark localization. Through experimental results on the DeepFashion dataset, we demonstrate that the proposed method has an excellent ability to learn deep feature representation for fashion recognition.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

S. Lee, S. Oh, C. Jung, C. Kim, "Fashion Landmark-Driven Feature Exploitation Network for Clothing Recognition," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 5, pp. 801-804, 2020. DOI: 10.7840/kics.2020.45.5.801.

[ACM Style]

Sumin Lee, Sungchan Oh, Chanho Jung, and Changick Kim. 2020. Fashion Landmark-Driven Feature Exploitation Network for Clothing Recognition. The Journal of Korean Institute of Communications and Information Sciences, 45, 5, (2020), 801-804. DOI: 10.7840/kics.2020.45.5.801.

[KICS Style]

Sumin Lee, Sungchan Oh, Chanho Jung, Changick Kim, "Fashion Landmark-Driven Feature Exploitation Network for Clothing Recognition," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 5, pp. 801-804, 5. 2020. (https://doi.org/10.7840/kics.2020.45.5.801)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880