| 本文已被：浏览 3086次 下载 5423次 |
码上扫一扫！ |
|
|
| 基于弱匹配概率典型相关性分析的图像自动标注 |
|
张博1, 郝杰2, 马刚3,4, 史忠植3
|
|
1.中国矿业大学 计算机科学与技术学院, 江苏 徐州 221116;2.徐州医科大学 医学信息学院, 江苏 徐州 221004;3.中国科学院 计算技术研究所 智能信息处理重点实验室, 北京 100190;4.中国科学院大学, 北京 100049
|
|
| 摘要: |
| 针对弱匹配多模态数据的相关性建模问题，提出了一种弱匹配概率典型相关性分析模型（semi-paired probabilistic CCA，简称SemiPCCA）.SemiPCCA模型关注于各模态内部的全局结构，模型参数的估计受到了未匹配样本的影响，而未匹配样本则揭示了各模态样本空间的全局结构.在人工弱匹配多模态数据集上的实验结果表明，SemiPCCA可以有效地解决传统CCA（canonical correlation analysis）和PCCA（probabilistic CCA）在匹配样本不足的情况下出现的过拟合问题，取得了较好的效果.提出了一种基于SemiPCCA的图像自动标注方法.该方法基于关联建模的思想，同时使用标注图像及其关键词和未标注图像学习视觉模态和文本模态之间的关联，从而能够更准确地对未知图像进行标注. |
| 关键词: 典型相关性分析 概率典型相关性分析 弱匹配典型相关性分析 图像自动标注 |
| DOI：10.13328/j.cnki.jos.005047 |
| 分类号: |
| 基金项目:国家重点基础研究发展计划（973）（2013CB329502）；国家自然科学基金（61035003）；国家高技术研究发展计划（863）（2012AA011003）；国家科技支撑计划（2012BA107B02）；江苏省自然科学基金（BK20160276） |
|
| Automatic Image Annotation Based on Semi-Paired Probabilistic Canonical Correlation Analysis |
|
ZHANG Bo1, HAO Jie2, MA Gang3,4, SHI Zhong-Zhi3
|
|
1.School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China;2.School of Medicine Information, Xuzhou Medical University, Xuzhou 221004, China;3.Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, The Chinese Academy of Sciences, Beijing 100190, China;4.University of Chinese Academy of Sciences, Beijing 100049, China
|
| Abstract: |
| Canonical correlation analysis (CCA) is a statistical analysis tool for analyzing the correlation between two sets of random variables. CCA requires the data be rigorously paired or one-to-one correspondence among different views due to its correlation definition. However, such requirement is usually not satisfied in real-world applications due to various reasons. Often, only a few paired and a lot of unpaired multi-view data are given, because unpaired multi-view data are relatively easier to be collected and pairing them is difficult, time consuming and even expensive. Such data is referred as semi-paired multi-view data. When facing semi-paired multi-view data, CCA usually performs poorly. To tackle this problem, a semi-paired variant of CCA, named SemiPCCA, is proposed based on the probabilistic model for CCA. The actual meaning of "semi-" in SemiPCCA is "semi-paired" rather than "semi-supervised" as in popular semi-supervised learning literature. The estimation of SemiPCCA model parameters is affected by the unpaired multi-view data which reveal the global structure within each modality. By using artificially generated semi-paired multi-view data sets, the experiment shows that SemiPCCA effectively overcome the over-fitting problem of traditional CCA and PCCA (probabilistic CCA) under the condition of insufficient paired multi-view data and performs better than the original CCA and PCCA. In addition, an automatic image annotation method based on the SemiPCCA is presented. Through estimating the relevance between images and words by using the labelled and unlabeled images together, this method is shown to be more accurate than previous published methods. |
| Key words: canonical correlation analysis probabilistic canonical correlation analysis semi-paired canonical correlation analysis automatic image annotation |
