Paper Doll Parsing: Retrieving Similar Styles to Parse Clothing Items
Authors:
- Kota YamaguchiKYKota Yamaguchi
- M. Hadi KiapourMKM. Hadi Kiapour
- Tamara L. BergTBTamara L. Berg
- 1 December 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 3519-3526
Abstract
Clothing recognition is an extremely challenging problem due to wide variation in clothing item appearance, layering, and style. In this paper, we tackle the clothing parsing problem using a retrieval based approach. For a query image, we find similar styles from a large database of tagged fashion images and use these examples to parse the query. Our approach combines parsing from: pre-trained global clothing models, local clothing models learned on the fly from retrieved examples, and transferred parse masks (paper doll item transfer) from retrieved examples. Experimental evaluation shows that our approach significantly outperforms state of the art in parsing accuracy.Keywords
This publication has 19 references indexed in Scilit:
- Finding Things: Image Parsing with Regions and Per-Exemplar Detectors2013
- Street-to-shop2012
- Hi, magic closet, tell me what to wear!2012
- Urban tribes: Analyzing group photos from a social perspective2012
- Predicting occupation via human clothing and contexts2011
- Accurate Object Recognition with Shape MasksInternational Journal of Computer Vision, 2011
- SIFT Flow: Dense Correspondence across Scenes and Its ApplicationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Segmentation using Deformable Spatial Priors with Application to Clothing2010
- Robust Object Detection with Interleaved Categorization and SegmentationInternational Journal of Computer Vision, 2007
- A Statistical Approach to Texture Classification from Single ImagesInternational Journal of Computer Vision, 2005