@inproceedings{250554b7bb7c48789352070c37644abc,
title = "Social image parsing by cross-modal data refinement",
abstract = "This paper presents a cross-modal data refinement algorithm for social image parsing, or segmenting all the objects within a social image and then identifying their categories. Different from the traditional fully supervised image parsing that takes pixel-level labels as strong supervisory information, our social image parsing is initially provided with the noisy tags of images (i.e. image-level labels), which are shared by social users. By oversegmenting each image into multiple regions, we formulate social image parsing as a cross-modal data refinement problem over a large set of regions, where the initial labels of each region are inferred from image-level labels. Furthermore, we develop an efficient algorithm to solve such cross-modal data refinement problem. The experimental results on several benchmark datasets show the effectiveness of our algorithm. More notably, our algorithm can be considered to provide an alternative and natural way to address the challenging problem of image parsing, since image-level labels are much easier to access than pixel-level labels.",
author = "Zhiwu Lu and Xin Gao and Songfang Huang and Liwei Wang and Wen, {Ji Rong}",
year = "2015",
language = "English (US)",
series = "IJCAI International Joint Conference on Artificial Intelligence",
publisher = "International Joint Conferences on Artificial Intelligence",
pages = "2169--2175",
editor = "Michael Wooldridge and Qiang Yang",
booktitle = "IJCAI 2015 - Proceedings of the 24th International Joint Conference on Artificial Intelligence",
note = "24th International Joint Conference on Artificial Intelligence, IJCAI 2015 ; Conference date: 25-07-2015 Through 31-07-2015",
}