Content-Based Image Annotation Refinement Export

@proceedings{citeulike:5724714, abstract = {Automatic image annotation has been an active research topic due to its great importance in image retrieval and management. However, results of the state-of-the-art image annotation methods are often unsatisfactory. Despite continuous efforts in inventing new annotation algorithms, it would be advantageous to develop a dedicated approach that could refine imprecise annotations. In this paper, a novel approach to automatically refining the original annotations of images is proposed. For a query image, an existing image annotation method is first employed to obtain a set of candidate annotations. Then, the candidate annotations are re-ranked and only the top ones are reserved as the final annotations. By formulating the annotation refinement process as a Markov process and defining the candidate annotations as the states of a Markov chain, a content-based image annotation refinement (CIAR) algorithm is proposed to re-rank the candidate annotations. It leverages both corpus information and the content feature of a query image. Experimental results on a typical Corel dataset show not only the validity of the refinement, but also the superiority of the proposed algorithm over existing ones.}, author = {Wang, Changhu and Jing, Feng and Zhang, Lei and Zhang, Hong-Jiang}, booktitle = {Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on}, citeulike-article-id = {5724714}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/CVPR.2007.383221}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4270246}, doi = {10.1109/CVPR.2007.383221}, journal = {Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on}, keywords = {annotations, folksonomies, tagging}, pages = {1--8}, posted-at = {2009-09-04 21:39:22}, priority = {2}, title = {Content-Based Image Annotation Refinement}, url = {http://dx.doi.org/10.1109/CVPR.2007.383221}, year = {2007} }

TY - CONF ID - citeulike:5724714 L3 - citeulike-article-id:5724714 N2 - Automatic image annotation has been an active research topic due to its great importance in image retrieval and management. However, results of the state-of-the-art image annotation methods are often unsatisfactory. Despite continuous efforts in inventing new annotation algorithms, it would be advantageous to develop a dedicated approach that could refine imprecise annotations. In this paper, a novel approach to automatically refining the original annotations of images is proposed. For a query image, an existing image annotation method is first employed to obtain a set of candidate annotations. Then, the candidate annotations are re-ranked and only the top ones are reserved as the final annotations. By formulating the annotation refinement process as a Markov process and defining the candidate annotations as the states of a Markov chain, a content-based image annotation refinement (CIAR) algorithm is proposed to re-rank the candidate annotations. It leverages both corpus information and the content feature of a query image. Experimental results on a typical Corel dataset show not only the validity of the refinement, but also the superiority of the proposed algorithm over existing ones. JF - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on EP - 8 TI - Content-Based Image Annotation Refinement T2 - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on SP - 1 KW - annotations KW - folksonomies KW - tagging AU - Wang, Changhu AU - Jing, Feng AU - Zhang, Lei AU - Zhang, Hong-Jiang PY - 2007/// UR - http://dx.doi.org/10.1109/CVPR.2007.383221 ER -