QQ客服 官方微博 反馈留言

	Joint Semantic Segmentation by Searching for Compatible-Competitive References
	Ping Luo; Xiaogang Wang; Liang Lin; Xiaoou Tang
	2012
会议名称	Proc. ACM Multimedia (ACM-MM), 2012
会议地点	日本
英文摘要	This paper presents a framework for semantically segmenting a tar- get image without tags by searching for references in an image database, where all the images are unsegmented but annotated with tags. We jointly segment the target image and its references by op- timizing both semantic consistencies within individual images and correspondences between the target image and each of its refer- ences. In our framework, we first retrieve two types of references with a semantic-driven scheme: i) the compatible references which share similar global appearance with the target image; and ii) the competitive references which have distinct appearance to the tar- get image but similar tags with one of the compatible references. The two types of references have complementary information for assisting the segmentation of the target image. Then we construct a novelgraphicalrepresentation, inwhichtheverticesaresuperpixels extracted from the target image and its references. The segmenta- tion problem is posed as labeling all the vertices with the seman- tic tags obtained from the references. The method is able to label images without the pixel-level annotation and classifier training, and it outperforms the state-of-the-arts approaches on the MSRC- 21 database.
收录类别	EI
语种	英语
内容类型	会议论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/3783]
专题	深圳先进技术研究院_集成所
作者单位	2012
推荐引用方式 GB/T 7714	Ping Luo,Xiaogang Wang,Liang Lin,et al. Joint Semantic Segmentation by Searching for Compatible-Competitive References[C]. 见:Proc. ACM Multimedia (ACM-MM), 2012. 日本.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。