Dual cross-media relevance model for image annotation
Dual cross-media relevance model for image annotation
复制标题
DOI：
10.1145/1291233.1291380
复制
发表时间：
2007-09
期刊：
影响因子：
--
通讯作者：
J. Liu;Bin Wang-;Mingjing Li;Zhiwei Li;Wei-Ying Ma;Hanqing Lu;Songde Ma
中科院分区：
文献类型：
--
作者：
J. Liu;Bin Wang-;Mingjing Li;Zhiwei Li;Wei-Ying Ma;Hanqing Lu;Songde Ma
图像注释近年来一直是一个积极的研究主题，因为它对图像理解和Web图像检索的潜在影响。现有的基于相关模型的方法通过最大化图像和单词的关节概率来执行图像注释，这是由对训练图像的期望计算得出的。但是，语义差距和对训练数据的依赖限制了它们的性能和可扩展性。在本文中，提出了一种自动图像注释的双跨媒体相关模型（DCMRM），该模型估计了预定词典中单词的期望值。 DCMRM在图像注释中涉及两种批判关系。一个是单词到图像的关系，另一个是单词到字的关系。可以通过在Web数据上使用搜索技术以及可用的培训数据来估算这两种关系。在Corel数据集和Web图像数据集上进行的实验证明了所提出的模型的有效性。
Image annotation has been an active research topic in recent years due to its potential impact on both image understanding and web image retrieval. Existing relevance-model-based methods perform image annotation by maximizing the joint probability of images and words, which is calculated by the expectation over training images. However, the semantic gap and the dependence on training data restrict their performance and scalability. In this paper, a dual cross-media relevance model (DCMRM) is proposed for automatic image annotation, which estimates the joint probability by the expectation over words in a pre-defined lexicon. DCMRM involves two kinds of critical relations in image annotation. One is the word-to-image relation and the other is the word-to-word relation. Both relations can be estimated by using search techniques on the web data as well as available training data. Experiments conducted on the Corel dataset and a web image dataset demonstrate the effectiveness of the proposed model.