TY - JOUR
T1 - Tag completion with defective tag assignments via image-tag re-weighting
AU - Xu, Xing
AU - Shimada, Atsushi
AU - Taniguchi, Rin Ichiro
N1 - Publisher Copyright:
© 2014 IEEE.
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
T2 - 2014 IEEE International Conference on Multimedia and Expo, ICME 2014
Y2 - 14 July 2014 through 18 July 2014
ER -