Distributed image understanding with semantic dictionary and semantic expansion | |
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 |
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. |
内容类型 | 期刊论文 |
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. |
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