Distributed image understanding with semantic dictionary and semantic expansion
文献类型：期刊论文
| 作者 | Liang Li ; Chenggang Clarence Yan; Xing Chen; Zhang Chunjie(张淳杰); Jian Yin; Baochen Jiang; Qingming Huang; Zhang CJ(张淳杰)
|
| 刊名 | Neurocomputing
 |
| 出版日期 | 2016 |
| 期号 | 174页码:384-392 |
| 关键词 | Image Understanding Semantic Dictionary Multi-task Learning Semantic Expansion Distributed Systems |
| 英文摘要 | Web-scaleimageunderstandingisdrawingmoreandmoreattentionfromthecomputervisionand multimedia domain.Tosolvethekeyproblemofvisualpolysemiaandconceptpolymorphisminthe image understanding,thispaperproposesasemanticdictionarytodescribetheimagesonthelevelof semantic. Thesemanticdictionarycharacterizestheprobabilitydistributionbetweenvisualappearances and semanticconcepts,andthelearningprocedureofsemanticdictionaryisformulatedintoamini- mization optimizationproblem.Mixed-normregularizationisadoptedtosolvetheaboveoptimization for learningtheconceptmembershipdistributionofvisualappearance.Furthermore,toimprovethe generalizationabilityofthesemanticdescription,weproposethesemanticexpansiontechnology,where a concepttransferringmatrixislearnttoquantizetheimplicitrelevancyamongtheconcepts.Finally,the distributed frameworkonthebasisofthesemanticdictionaryisconstructedtospeedupthelargescale image understanding.Thesemanticdictionaryisvalidatedinthetasksoflargescalesemanticimage search andimageannotation. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/20409]  |
| 专题 | 自动化研究所_类脑智能研究中心 |
| 通讯作者 | Zhang CJ(张淳杰) |
| 推荐引用方式 GB/T 7714 | Liang Li,Chenggang Clarence Yan,Xing Chen,et al. Distributed image understanding with semantic dictionary and semantic expansion[J]. Neurocomputing,2016(174):384-392. |
| APA | Liang Li.,Chenggang Clarence Yan.,Xing Chen.,Zhang Chunjie.,Jian Yin.,...&张淳杰.(2016).Distributed image understanding with semantic dictionary and semantic expansion.Neurocomputing(174),384-392. |
| MLA | Liang Li,et al."Distributed image understanding with semantic dictionary and semantic expansion".Neurocomputing .174(2016):384-392. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。