Non-negative Matrix Factorization in Multimodality Data for Segmentation and Label Prediction
Non-negative Matrix Factorization in Multimodality Data for Segmentation and Label Prediction
复制标题
DOI：
--
复制
发表时间：
2011-02
期刊：
影响因子：
--
通讯作者：
Zeynep Akata;Christian Thurau;C. Bauckhage
中科院分区：
文献类型：
--
作者：
Zeynep Akata;Christian Thurau;C. Bauckhage
随着带注释的多媒体数据在因特网上的可用性越来越高，需要允许对不同类型的数据进行原则性联合处理的技术。多视点学习和多视点聚类试图同时识别不同特征空间中的潜在成分。由此得到的基矢量或质心忠实地代表了对数据的不同观点，但它们是隐含地耦合的，它们是联合估计的。这为解决标签预测、图像检索或语义分组等问题开辟了新的途径。本文提出了一种新的多视图聚类模型，将传统的非负矩阵分解扩展到不同数据矩阵的联合分解。因此，该技术为图像部分和属性的联合处理提供了一种新的方法。首先，在图像分割和图像特征和图像标签的多视角聚类实验中取得了令人满意的结果，表明该方法为不同抽象层次的图像分析提供了一个通用的框架。
With the increasing availability of annotated multimedia data on the Internet, techniques are in demand that allow for a principled joint processing of different types of data. Multiview learning and multiview clustering attempt to identify latent components in different features spaces in a simultaneous manner. The resulting basis vectors or centroids faithfully represent the different views on the data but are implicitly coupled and they were jointly estimated. This opens new avenues to problems such as label prediction, image retrieval, or semantic grouping. In this paper, we present a new model for multiview clustering that extends traditional non-negative matrix factorization to the joint factorization of different data matrices. Accordingly, the technique provides a new approach to the joint treatment of image parts and attributes. First experiments in image segmentation and multiview clustering of image features and image labels show promising results and indicate that the proposed method offers a common framework for image analysis on different levels of abstraction.