Image annotation via learning the image-label interrelations

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 先进时空数据分析与学习

	Image annotation via learning the image-label interrelations
	Yonghao He; Jian Wang; Shiming Xiang; Chunhong Pan; He,Yonghao
	2014
会议名称	ICIP2014
会议录名称	International Conference on Image Processing (ICIP)
页码	3102-3106
会议日期	2014
会议地点	Pairs, French
摘要	The goal of image annotation is to automatically assign meaningful and content-related labels to the digital images by using machines. It is beneficial to image search and image sharing in social networks. Various methods for image annotation are proposed in last decade and they have gained much progress. However, most of them are not precise and fast enough for real-world applications. In this paper, we propose a novel and fast image annotation method via learning the image-label interrelation. The main idea of the proposed method is to predict labels by linearly propagating the label information through the image-label interrelation and the image similarities. Thus, we propose a model based on the regression between the label groundtruth and the propagated label information to learn the image-label interrelation. In addition, a label-biased regularization is integrated into our model to learn more effective and meaningful image-label interrelation. Finally, our model can be solved in closed form, therefore it achieves a fast learning process. Experimental results on three benchmark datasets demonstrate that our method shows the comparable performance with state-of-theart methods and has faster learning time.
关键词	Image Annotation Image-label Interrelation
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/4737
专题	多模态人工智能系统全国重点实验室_先进时空数据分析与学习
通讯作者	He,Yonghao
推荐引用方式 GB/T 7714	Yonghao He,Jian Wang,Shiming Xiang,et al. Image annotation via learning the image-label interrelations[C],2014:3102-3106.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Image annotation via（656KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载