Large Image/Videos Automatic Annotation Using Bidirectional Associative Memories

摘要：

In this paper,an approach of image/videosautomatic annotation considering semanticstolerance relation between pre-defined classes isdescribed.The image/videossemantics is representedby a vector of associative values with the pre-definedclasses.Moreover,the semantic gap induced in theprocess of automatically generating associative valuesis dealt with by using the constructed semantictolerance relation model(STRM).On the other hand,the method how to generating associative values withpre-defined classes regarding different dimensions isalso depicted Image/videosretrieval results basedon the pre-defined classes shows the effectiveness ofthe proposed methods.

作者: Ying Dai

作者单位: Iwate Pref University

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 565-571

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）