Tag completion with defective tag assignments via image-tag re-weighting

研究成果: ジャーナルへの寄稿Conference article

6 引用 (Scopus)

抄録

User-provided image tags are usually incomplete or noisy to describe the visual content of corresponding images. In this paper, we consider defective tagging which covers both incomplete and noisy situations, and address the problem of tag completion where tag assignments of training images are defective. While previous studies on tag completion usually assign equal penalty to empirical loss when processing each missing or noisy tag for each image, we show that this may be suboptimal as the relatedness of each tag to each image varies due to the defective setting. Thus, we introduce an image-tag re-weighting scheme to re-weight the penalty term of each tag to each image considering both image similarities and tag associations, and formulate a unified re-weighted empirical loss function. Experimental evaluations show that embedding proposed re-weighted empirical loss function in state-of-the-art tag completion algorithms achieves significant improvement in dealing with defective tag assignments.

元の言語英語
記事番号6890154
ジャーナルProceedings - IEEE International Conference on Multimedia and Expo
2014-September
発行部数Septmber
DOI
出版物ステータス出版済み - 9 3 2014
イベント2014 IEEE International Conference on Multimedia and Expo, ICME 2014 - Chengdu, 中国
継続期間: 7 14 20147 18 2014

Fingerprint

Processing

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications

これを引用

Tag completion with defective tag assignments via image-tag re-weighting. / Xu, Xing; Shimada, Atsushi; Taniguchi, Rin-Ichiro.

:: Proceedings - IEEE International Conference on Multimedia and Expo, 巻 2014-September, 番号 Septmber, 6890154, 03.09.2014.

研究成果: ジャーナルへの寄稿Conference article

@article{837508c8e39b49a78b22ff190e0a5a57,
title = "Tag completion with defective tag assignments via image-tag re-weighting",
abstract = "User-provided image tags are usually incomplete or noisy to describe the visual content of corresponding images. In this paper, we consider defective tagging which covers both incomplete and noisy situations, and address the problem of tag completion where tag assignments of training images are defective. While previous studies on tag completion usually assign equal penalty to empirical loss when processing each missing or noisy tag for each image, we show that this may be suboptimal as the relatedness of each tag to each image varies due to the defective setting. Thus, we introduce an image-tag re-weighting scheme to re-weight the penalty term of each tag to each image considering both image similarities and tag associations, and formulate a unified re-weighted empirical loss function. Experimental evaluations show that embedding proposed re-weighted empirical loss function in state-of-the-art tag completion algorithms achieves significant improvement in dealing with defective tag assignments.",
author = "Xing Xu and Atsushi Shimada and Rin-Ichiro Taniguchi",
year = "2014",
month = "9",
day = "3",
doi = "10.1109/ICME.2014.6890154",
language = "English",
volume = "2014-September",
journal = "Proceedings - IEEE International Conference on Multimedia and Expo",
issn = "1945-7871",
number = "Septmber",

}

TY - JOUR

T1 - Tag completion with defective tag assignments via image-tag re-weighting

AU - Xu, Xing

AU - Shimada, Atsushi

AU - Taniguchi, Rin-Ichiro

PY - 2014/9/3

Y1 - 2014/9/3

N2 - User-provided image tags are usually incomplete or noisy to describe the visual content of corresponding images. In this paper, we consider defective tagging which covers both incomplete and noisy situations, and address the problem of tag completion where tag assignments of training images are defective. While previous studies on tag completion usually assign equal penalty to empirical loss when processing each missing or noisy tag for each image, we show that this may be suboptimal as the relatedness of each tag to each image varies due to the defective setting. Thus, we introduce an image-tag re-weighting scheme to re-weight the penalty term of each tag to each image considering both image similarities and tag associations, and formulate a unified re-weighted empirical loss function. Experimental evaluations show that embedding proposed re-weighted empirical loss function in state-of-the-art tag completion algorithms achieves significant improvement in dealing with defective tag assignments.

AB - User-provided image tags are usually incomplete or noisy to describe the visual content of corresponding images. In this paper, we consider defective tagging which covers both incomplete and noisy situations, and address the problem of tag completion where tag assignments of training images are defective. While previous studies on tag completion usually assign equal penalty to empirical loss when processing each missing or noisy tag for each image, we show that this may be suboptimal as the relatedness of each tag to each image varies due to the defective setting. Thus, we introduce an image-tag re-weighting scheme to re-weight the penalty term of each tag to each image considering both image similarities and tag associations, and formulate a unified re-weighted empirical loss function. Experimental evaluations show that embedding proposed re-weighted empirical loss function in state-of-the-art tag completion algorithms achieves significant improvement in dealing with defective tag assignments.

UR - http://www.scopus.com/inward/record.url?scp=84937469086&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937469086&partnerID=8YFLogxK

U2 - 10.1109/ICME.2014.6890154

DO - 10.1109/ICME.2014.6890154

M3 - Conference article

AN - SCOPUS:84937469086

VL - 2014-September

JO - Proceedings - IEEE International Conference on Multimedia and Expo

JF - Proceedings - IEEE International Conference on Multimedia and Expo

SN - 1945-7871

IS - Septmber

M1 - 6890154

ER -