Please use this identifier to cite or link to this item: https://doi.org/10.1109/TMM.2013.2285526
Title: Fashion parsing with weak color-category labels
Authors: Liu, S. 
Feng, J.
Domokos, C.
Xu, H.
Huang, J.
Hu, Z.
Yan, S. 
Keywords: Fashion parsing
Markov random fields
weakly-supervised learning
Issue Date: Jan-2014
Citation: Liu, S., Feng, J., Domokos, C., Xu, H., Huang, J., Hu, Z., Yan, S. (2014-01). Fashion parsing with weak color-category labels. IEEE Transactions on Multimedia 16 (1) : 253-265. ScholarBank@NUS Repository. https://doi.org/10.1109/TMM.2013.2285526
Abstract: In this paper we address the problem of automatically parsing the fashion images with weak supervision from the user-generated color-category tags such as 'red jeans' and 'white T-shirt'. This problem is very challenging due to the large diversity of fashion items and the absence of pixel-level tags, which make the traditional fully supervised algorithms inapplicable. To solve the problem, we propose to combine the human pose estimation module, the MRF-based color and category inference module and the (super)pixel-level category classifier learning module to generate multiple well-performing category classifiers, which can be directly applied to parse the fashion items in the images. Besides, all the training images are parsed with color-category labels and the human poses of the images are estimated during the model learning phase in this work. We also construct a new fashion image dataset called Colorful-Fashion, in which all 2,682 images are labeled with pixel-level color-category labels. Extensive experiments on this dataset clearly show the effectiveness of the proposed method for the weakly supervised fashion parsing task. © 1999-2012 IEEE.
Source Title: IEEE Transactions on Multimedia
URI: http://scholarbank.nus.edu.sg/handle/10635/56004
ISSN: 15209210
DOI: 10.1109/TMM.2013.2285526
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.