Auto face re-ranking by mining the web and video archives
Auto face re-ranking by mining the web and video archives
复制标题
DOI：
10.1109/cvpr.2012.6248025
复制
发表时间：
2012-06
期刊：
影响因子：
--
通讯作者：
Duy-Dinh Le;S. Satoh
中科院分区：
文献类型：
--
作者：
Duy-Dinh Le;S. Satoh
在使用文本信息进行索引的图像搜索引擎中，有必要利用视觉信息来提高检索效率。一种流行的方法是学习这些搜索引擎返回的图像之间的视觉一致性。大多数最先进的学习视觉一致性的方法通常会为每个查询学习一个特定的分类器，以对返回的图像进行重新排序。这些基于查询特定的方法的主要缺点是它们需要计算成本和处理时间，不适合处理大量查询。另一种方法是学习一个通用分类器一次，然后用于所有查询。遵循基于通用分类器的方法，我们研究了对现有搜索引擎返回的面孔进行重新排名以提高检索性能的问题。学习通用分类器涉及找到良好的依赖于查询的特征表示并收集足够多的训练样本。现有的工作 [9, 15] 研究一般对象而不是面部的查询相关特征。此外，训练样本通常是手动收集的。这项研究的关键贡献是引入了人脸的查询相关特征和自动收集训练样本以学习通用分类器的无监督方法。实验结果表明，所提出的方法在各种数据集中都表现良好。
It is necessary to utilize visual information to improve the efficiency of retrieval in image-search engines that use textual information for indexing. One popular approach has been to learn visual consistency between images returned by these search engines. Most state-of-the-art methods of learning visual consistency usually learn one specific classifier for each query to re-rank the returned images. The main drawback with these query-specific based methods is that they require computational cost and processing time that are unsuitable for handling a large number of queries. Another approach has been to learn one generic classifier once and then use for all queries. Pursuing the generic classifier based approach, we study the problem of re-ranking faces returned by existing search engines to improve retrieval performance. Learning a generic classifier involves finding good query-dependent feature representation and collecting sufficient large number of training samples. Existing work [9, 15] studies query-dependent features for general objects rather than faces. In addition, training samples are usually collected manually. The key contribution of this research is to introduce a query-dependent feature for faces and an unsupervised method of automatically collecting training samples to learn the generic classifier. The experimental results demonstrated that the proposed method performed very well in various datasets.