Image Tag Completion via Image-Specific and Tag-Specific Linear Sparse Reconstructions

Zijia Lin, Guiguang Ding, Mingqing Hu, Jianmin Wang, Xiaojun Ye; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 1618-1625

Abstract


Though widely utilized for facilitating image management, user-provided image tags are usually incomplete and insufficient to describe the whole semantic content of corresponding images, resulting in performance degradations in tag-dependent applications and thus necessitating effective tag completion methods. In this paper, we propose a novel scheme denoted as LSR for automatic image tag completion via image-specific and tag-specific Linear Sparse Reconstructions. Given an incomplete initial tagging matrix with each row representing an image and each column representing a tag, LSR optimally reconstructs each image (i.e. row) and each tag (i.e. column) with remaining ones under constraints of sparsity, considering imageimage similarity, image-tag association and tag-tag concurrence. Then both image-specific and tag-specific reconstruction values are normalized and merged for selecting missing related tags. Extensive experiments conducted on both benchmark dataset and web images well demonstrate the effectiveness of the proposed LSR.

Related Material


[pdf]
[bibtex]
@InProceedings{Lin_2013_CVPR,
author = {Lin, Zijia and Ding, Guiguang and Hu, Mingqing and Wang, Jianmin and Ye, Xiaojun},
title = {Image Tag Completion via Image-Specific and Tag-Specific Linear Sparse Reconstructions},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}