A probabilistic semantic model for image annotation and multimodal image retrieval Export

@inproceedings{citeulike:1696829, abstract = {This paper addresses automatic image annotation problem and its application to multi-modal image retrieval. The contribution of our work is three-fold. (1) We propose a probabilistic semantic model in which the visual features and the textual words are connected via a hidden layer which constitutes the semantic concepts to be discovered to explicitly exploit the synergy among the modalities. (2) The association of visual features and textual words is determined in a Bayesian framework such that the confidence of the association can be provided. (3) Extensive evaluation on a large-scale, visually and semantically diverse image collection crawled from Web is reported to evaluate the prototype system based on the model. In the proposed probabilistic model, a hidden concept layer which connects the visual feature and the word layer is discovered by fitting a generative model to the training image and annotation words through an Expectation-Maximization (EM) based iterative learning procedure. The evaluation of the prototype system on 17,000 images and 7,736 automatically extracted annotation words from crawled Web pages for multi-modal image retrieval has indicated that the proposed semantic model and the developed Bayesian framework are superior to a state-of-the-art peer system in the literature.}, author = {Zhang, Ruofei and Zhang, Zhongfei and Li, Mingjing and Ma, Wei-Ying and Zhang, Hong-Jiang}, booktitle = {Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on}, citeulike-article-id = {1696829}, citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1541341}, journal = {Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on}, pages = {846--851 Vol. 1}, posted-at = {2007-09-26 11:17:48}, priority = {5}, title = {A probabilistic semantic model for image annotation and multimodal image retrieval}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1541341}, volume = {1}, year = {2005} }

TY - CONF ID - citeulike:1696829 L3 - citeulike-article-id:1696829 N2 - This paper addresses automatic image annotation problem and its application to multi-modal image retrieval. The contribution of our work is three-fold. (1) We propose a probabilistic semantic model in which the visual features and the textual words are connected via a hidden layer which constitutes the semantic concepts to be discovered to explicitly exploit the synergy among the modalities. (2) The association of visual features and textual words is determined in a Bayesian framework such that the confidence of the association can be provided. (3) Extensive evaluation on a large-scale, visually and semantically diverse image collection crawled from Web is reported to evaluate the prototype system based on the model. In the proposed probabilistic model, a hidden concept layer which connects the visual feature and the word layer is discovered by fitting a generative model to the training image and annotation words through an Expectation-Maximization (EM) based iterative learning procedure. The evaluation of the prototype system on 17,000 images and 7,736 automatically extracted annotation words from crawled Web pages for multi-modal image retrieval has indicated that the proposed semantic model and the developed Bayesian framework are superior to a state-of-the-art peer system in the literature. JF - Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on EP - 851 Vol. 1 TI - A probabilistic semantic model for image annotation and multimodal image retrieval VL - 1 T2 - Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on SP - 846 AU - Zhang, Ruofei AU - Zhang, Zhongfei AU - Li, Mingjing AU - Ma, Wei-Ying AU - Zhang, Hong-Jiang PY - 2005/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1541341 ER -