Combining attention model with hierarchical graph representation for region-based image retrieval

CASIA OpenIR > 09年以前成果

	Combining attention model with hierarchical graph representation for region-based image retrieval
	Songhe Feng; De Xu; Bing Li
发表期刊	IEICE Trans. On Inf. & Sys.
	2008
卷号	E91-D 期号:8 页码:2203-2206
摘要	The manifold-ranking algorithm has been successfully adopted in content-based image retrieval (CBIR) in recent years. However, while the global low-level features are widely utilized in current systems, region-based features have received little attention. In this paper, a novel attention-driven transductive framework based on a hierarchical graph representation is proposed for region-based image retrieval (RBIR). This approach can be characterized by two key properties: (1) Since the issue about region significance is the key problem in region-based retrieval, a visual attention model is chosen here to measure the regions' significance. (2) A hierarchical graph representation which combines region-level with image-level similarities is utilized for the manifold-ranking method. A novel propagation energy function is defined which takes both low-level visual features and regional significance into consideration. Experimental results demonstrate that the proposed approach shows the satisfactory retrieval performance compared to the global-based and the block-based manifold-ranking methods.
关键词	Image Retrieval
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/20392
专题	09年以前成果
作者单位	Beijing Jiaotong University
推荐引用方式 GB/T 7714	Songhe Feng,De Xu,Bing Li. Combining attention model with hierarchical graph representation for region-based image retrieval[J]. IEICE Trans. On Inf. & Sys.,2008,E91-D(8):2203-2206.
APA	Songhe Feng,De Xu,&Bing Li.(2008).Combining attention model with hierarchical graph representation for region-based image retrieval.IEICE Trans. On Inf. & Sys.,E91-D(8),2203-2206.
MLA	Songhe Feng,et al."Combining attention model with hierarchical graph representation for region-based image retrieval".IEICE Trans. On Inf. & Sys. E91-D.8(2008):2203-2206.