...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Optical engineering >Modeling loosely annotated images using both given and imagined annotations
【24h】

Modeling loosely annotated images using both given and imagined annotations

机译：使用给定和想象的注释对松散注释的图像进行建模

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we present an approach to learn latent semantic analysis models from loosely annotated images for automatic image an-notation and indexing. The given annotation in training images is loose due to: 1. ambiguous correspondences between visual features and an-notated keywords; 2. incomplete lists of annotated keywords. The second reason motivates us to enrich the incomplete annotation in a simple way before learning a topic model. In particular, some "imagined" keywords are poured into the incomplete annotation through measuring similarity between keywords in terms of their co-occurrence. Then, both given and imagined annotations are employed to learn probabilistic topic models for automatically annotating new images. We conduct experiments on two im-age databases (i.e., Corel and ESP) coupled with their loose annotations, and compare the proposed method with state-of-the-art discrete anno-tation methods. The proposed method improves word-driven probability latent semantic analysis (PLSA-words) up to a comparable performance with the best discrete annotation method, while a merit of PLSA-words is still kept, i.e., a wider semantic range.
机译：在本文中，我们提出了一种从松散注释的图像中学习潜在语义分析模型的方法，以进行自动的图像注释和索引。训练图像中的给定注释由于以下原因而松散：1.视觉特征与带注释的关键字之间的对应不明确； 2.带注释的关键字列表不完整。第二个原因促使我们在学习主题模型之前以简单的方式丰富不完整的注释。特别是，通过测量关键字之间的相似度，将一些“想象中的”关键字注入到不完整注释中。然后，使用给定和想象中的注释来学习概率主题模型，以自动注释新图像。我们在两个图像数据库（即Corel和ESP）以及松散的注释上进行了实验，并将该方法与最新的离散注释方法进行了比较。所提出的方法将单词驱动的概率潜在语义分析（PLSA-words）改进到与最佳离散注释方法可比的性能，同时仍然保留了PLSA-words的优点，即语义范围更广。

著录项

  • 来源
    《Optical engineering》 |2011年第12期|p.127004.1-127004.8|共8页
  • 作者

    Hong Tang; Nozha Boujemaa; Yunhao Chen; Lei Deng;

  • 作者单位

    Beijing Normal University Key Laboratory of Environment Change and Natural Disaster Beijing 100875 China Beijing Normal University State Key Laboratory of Earth Surface Processes and Resource Ecology Beijing 100875, China;

    INRIA Project IMEDIA Le Chesnay 78153, France;

    Beijing Normal University State Key Laboratory of Earth Surface Processes and Resource Ecology Beijing 100875, China;

    Capital Normal University College of Resource Environment and T ourismBeijing 100048, China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    image annotation; probabilistic latent semantic analysis; imageretrieval;

    机译：图像注释;概率潜在语义分析;图像检索;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号