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。
修改评论