基于社会标签的图像标注与标签推荐

With the permeation of Web 2.0, large-scale user contributed images with tags are easily available on social websites. Due to the subjectivity and diversity of such social tagging, noisy and missing tags for images are inevitable, which limits the performance of tag-based image retrieval system. In this proposal, we aim to solve the problems of image annotation and tag recommendation by exploring the correlations among images, tags, and users, in which the usage of the social tags should be taken more attention. We plan to carry out the project from the following aspects: (1) hierarchical structure learning and correlation estimation for social tags; (2) semantic-incorporated image representation and similarity measure; (3) improved matrix factorization for image annotation; (4) image tag recommendation based on user preference learning. It is noted that image annotation and tag recommendation are boosted each other. Due to the decreased tagging cost brought by tag recommendation, more users are willing to tag images, then more high-quality tagging data can be obtained for image annotation methods. In addition, the results of image annotation can provide prior guidance for image tag recommendation. We believe that the union of image annotation and tag recommendation make it possible to indexing and search the large-scale web resources incrementally and effectively.

基于社会标签在网络图片资源传播分享中的重要作用，同时考虑到因其自由性和开放性而带来的多噪声、稀疏性、主观性等问题，本项目将以图片分享网站的社会标签、图像与用户数据为研究对象，合理考虑三者之间动态交互关系，重点发掘社会标签数据在语义空间学习、图像特征表示、图像标注及其标签推荐等方面所能提供的有用知识，具体展开以下研究内容：（1）社会标签的层次关系发现及其相关性分析；（2）融合高层语义的图像特征表示及其相关性分析；（3）基于矩阵分解模型的图像-标签关联分析（即图像标注）；（4）基于用户偏好学习的图像标签推荐。其中，图像标签推荐可降低用户标注代价，提高标注数据质量与数量，进而为图像标注提供更好的数据基础；反过来，图像标注可为用户要标记的图像提供其语义标签的先验排序，以此为标签推荐提供指导。二者的有机结合是维持网络共享资源的增量式高效管理与准确索引的有力保证。

在本项目支持下，项目组成果深入探索和研究了基于社会标签的图像标注与标签推荐问题，重点研究了基于知识与数据混合驱动的图像特征鲁棒表示、基于鲁棒结构子空间学习的图像-标签关联映射以及基于统一嵌入子空间的图像标签推荐等方面，取得了较为丰硕的研究成果，较好的实现了预期研究目标。项目组成员共发表高质量的学术论文36篇，其中有包括IEEE T-KDE、IEEE T-NNLS、IEEE T-MM、Pattern Recognition等重要国际期刊论文21篇，CVPR、ACM MM、WWW等重要国际会议论文15篇；申请国家发明专利4项，其中已授权专利3项。培养硕博连读研究生共6名，其中已毕业4名。本项目在理论方法研究成果基础上，收集近百万幅网络图像及其相关社会标签信息，设计开发了一套基于安卓平台的图像标注与标签推荐的集成验证系统。