Unsupervised people organization and its application on individual retrieval from videos
Unsupervised people organization and its application on individual retrieval from videos
复制标题
DOI：
--
复制
发表时间：
2012-12
期刊：
影响因子：
--
通讯作者：
Pengyi Hao;S. Kamata
中科院分区：
文献类型：
--
作者：
Pengyi Hao;S. Kamata
本文提出了一种基于场景轨迹的直方图相交度量学习方法，用于视频中人物的自动组织。我们做出了以下贡献：（i）学习直方图相交距离，而不是广泛使用的人脸特征的Mahalanobis距离;（ii）从场景轨迹中学习度量，而无需手动标记任何示例，这使得能够在姿势，表情，遮挡和照明的大变化中学习，并且可以有效地区分不同的人。我们首先测试人脸识别，跟踪聚类和人员组织的一个长的电影，然后从一个大型的视频数据集的人组织的基础上的个人检索进行评估，证明显着提高搜索质量相对于以前的方法在这方面。
In this paper, a method named histogram intersection metric learning from scene tracks is proposed for automatic organizing people in videos. We make the following contributions: (i) learning histogram intersection distance instead of Mahalanobis distance for widely used face features; (ii) learning the metric from scene tracks without manually labeling any examples, which enables learning across large variations in pose, expression, occlusion and illumination with small number of face pairs and can distinguish different people powerfully. We firstly test face identification, track clustering, and people organization on a long film, then individual retrieval based on people organization from a large video dataset is evaluated, demonstrating significantly increased search quality with respect to previous approaches on this area.