QQ客服 官方微博 反馈留言

	A Novel Cross-Modal Topic Correlation Model for Cross-Media Retrieval
	Cheng, Yong1; Huang, Fei1; Jin, Cheng1; Zhang, Yuejie1; Zhang, Tao2
	2016
卷号	285
DOI	10.3233/978-1-61499-672-9-399
页码	399-407
英文摘要	A novel cross-modal topic correlation model CMTCM is developed in this paper to facilitate more effective cross-modal analysis and cross-media retrieval for large-scale multimodal document collections. It can be modeled as a cross-modal topic correlation model which explores the inter-related correlation distribution over the deep representations of multimodal documents. It integrates the deep multimodal document representation, relational topic correlation modeling, and cross-modal topic correlation learning, which aims to characterize the correlations between the heterogeneous topic distributions of inter-related visual images and semantic texts, and measure their association degree more precisely. Very positive results were obtained in our experiments using a large quantity of public data.
会议录出版者	IOS PRESS
会议录出版地	NIEUWE HEMWEG 6B, 1013 BG AMSTERDAM, NETHERLANDS
语种	英语
WOS研究方向	Computer Science
WOS记录号	WOS:000385793700048
内容类型	会议论文
源URL	[http://10.2.47.112/handle/2XS4QKH4/3372]
专题	上海财经大学
作者单位	1.Fudan Univ, Sch Comp Sci, Shanghai Key Lab Intelligent Informat Proc, Shanghai, Peoples R China; 2.Shanghai Univ Finance & Econ, Sch Informat Management & Engn, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Cheng, Yong,Huang, Fei,Jin, Cheng,et al. A Novel Cross-Modal Topic Correlation Model for Cross-Media Retrieval[C]. 见:.

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。