Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICCV.2013.423
Title: A deformable mixture parsing model with parselets
Authors: Dong, J.
Chen, Q.
Xia, W.
Huang, Z.
Yan, S. 
Issue Date: 2013
Citation: Dong, J., Chen, Q., Xia, W., Huang, Z., Yan, S. (2013). A deformable mixture parsing model with parselets. Proceedings of the IEEE International Conference on Computer Vision : 3408-3415. ScholarBank@NUS Repository. https://doi.org/10.1109/ICCV.2013.423
Abstract: In this work, we address the problem of human parsing, namely partitioning the human body into semantic regions, by using the novel Parse let representation. Previous works often consider solving the problem of human pose estimation as the prerequisite of human parsing. We argue that these approaches cannot obtain optimal pixel level parsing due to the inconsistent targets between these tasks. In this paper, we propose to use Parse lets as the building blocks of our parsing model. Parse lets are a group of parsable segments which can generally be obtained by low-level over-segmentation algorithms and bear strong semantic meaning. We then build a Deformable Mixture Parsing Model~(DMPM) for human parsing to simultaneously handle the deformation and multi-modalities of Parse lets. The proposed model has two unique characteristics: (1) the possible numerous modalities of Parse let ensembles are exhibited as the "And-Or' structure of sub-trees, (2) to further solve the practical problem of Parse let occlusion or absence, we directly model the visibility property at some leaf nodes. The DMPM thus directly solves the problem of human parsing by searching for the best graph configuration from a pool of Parse let hypotheses without intermediate tasks. Comprehensive evaluations demonstrate the encouraging performance of the proposed approach. © 2013 IEEE.
Source Title: Proceedings of the IEEE International Conference on Computer Vision
URI: http://scholarbank.nus.edu.sg/handle/10635/83345
ISBN: 9781479928392
DOI: 10.1109/ICCV.2013.423
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

31
checked on Aug 11, 2018

WEB OF SCIENCETM
Citations

12
checked on Jul 25, 2018

Page view(s)

39
checked on Jun 29, 2018

Google ScholarTM

Check

Altmetric


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