Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Beyond Photo-Domain Object Recognition: Benchmarks for the Cross-Depiction Problem
Author: Cai, H.
Wu, Q.
Hall, P.
Citation: Proceedings / IEEE International Conference on Computer Vision. IEEE International Conference on Computer Vision, 2015, vol.2015-February, pp.74-79
Publisher: IEEE
Issue Date: 2015
ISBN: 9781467383905
ISSN: 1550-5499
Conference Name: IEEE International Conference on Computer Vision Workshops (ICCVW) (11 Dec 2015 - 18 Dec 2015 : Santigo)
Statement of
Hongping Cai, Qi Wu, Peter Hall
Abstract: The cross-depiction problem is that of recognising visual objects regardless of whether they are photographed, painted, drawn, etc. It introduces great challenge as the variance across photo and art domains is much larger than either alone. We extensively evaluate classification, domain adaptation and detection benchmarks for leading techniques, demonstrating that none perform consistently well given the cross-depiction problem. Finally we refine the DPM model, based on query expansion, enabling it to bridge the gap across depiction boundaries to some extent.
Rights: © 2015 IEEE
DOI: 10.1109/ICCVW.2015.19
Published version:
Appears in Collections:Aurora harvest 8
Computer Science publications

Files in This Item:
File Description SizeFormat 
  Restricted Access
Restricted Access400.06 kBAdobe PDFView/Open

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