The Community for Technology Leaders
CVPR 2011 (2011)
Providence, RI
June 20, 2011 to June 25, 2011
ISBN: 978-1-4577-0394-2
pp: 881-888
Yang Yang , Univ. of Queensland, Brisbane, QLD, Australia
Yi Yang , Univ. of Queensland, Brisbane, QLD, Australia
Zi Huang , Univ. of Queensland, Brisbane, QLD, Australia
Heng Tao Shen , Univ. of Queensland, Brisbane, QLD, Australia
Feiping Nie , Univ. of Texas Arlington, Arlington, TX, USA
ABSTRACT
Nowadays numerous social images have been emerging on the Web. How to precisely label these images is critical to image retrieval. However, traditional image-level tagging methods may become less effective because global image matching approaches can hardly cope with the diversity and arbitrariness of Web image content. This raises an urgent need for the fine-grained tagging schemes. In this work, we study how to establish mapping between tags and image regions, i.e. localize tags to image regions, so as to better depict and index the content of images. We propose the spatial group sparse coding (SGSC) by extending the robust encoding ability of group sparse coding with spatial correlations among training regions. We present spatial correlations in a two-dimensional image space and design group-specific spatial kernels to produce a more interpretable regularizer. Further we propose a joint version of the SGSC model which is able to simultaneously encode a group of intrinsically related regions within a test image. An effective algorithm is developed to optimize the objective function of the Joint SGSC. The tag localization task is conducted by propagating tags from sparsely selected groups of regions to the target regions according to the reconstruction coefficients. Extensive experiments on three public image datasets illustrate that our proposed models achieve great performance improvements over the state-of-the-art method in the tag localization task.
INDEX TERMS
public image datasets, tag localization, spatial correlation, joint group sparsity, social images, image retrieval, image-level tagging method, image matching, Web image content, fine-grained tagging scheme, image regions, spatial group sparse coding, robust encoding ability, two-dimensional image space, group-specific spatial kernels, joint SGSC, reconstruction coefficients
CITATION

Feiping Nie, Yang Yang, Heng Tao Shen, Zi Huang and Yi Yang, "Tag localization with spatial correlations and joint group sparsity," CVPR 2011(CVPR), Providence, RI, 2011, pp. 881-888.
doi:10.1109/CVPR.2011.5995499
231 ms
(Ver 3.3 (11022016))