中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 机器人应用与理论组
Image recommendation based on a novel biologically inspired hierarchical model

文献类型：期刊论文

作者Lu, Yan-Feng1; Qiao, Hong2,3; Li, Yi4; Jia, Li-Hao1
刊名MULTIMEDIA TOOLS AND APPLICATIONS
出版日期2018-02-01
卷号77期号:4页码:4323-4337
关键词Image Recommendation Classification Biologically Inspired Model Image Retrieval Feature Representation
DOI10.1007/s11042-017-5514-z
文献子类Article
英文摘要Image recommendation has become an increasingly relevant problem recently, since strong demand to quickly find interested images from vast amounts of image library. We describe a biologically inspired hierarchical model for image recommendation. The biologically inspired model (BIM) for invariant feature representation has attracted widespread attention, which approximately follows the organization of cortex visuel. BIM is a computation architecture with four layers. With the image data size increases, the four-layer framework is prone to be overfitting, which limits its application. To address this issue, we propose a biologically inspired hierarchical model (BIHM) for feature representation, which adds two more discriminative layers upon the conventional four-layer framework. In contrast to the conventional BIM that mimics the inferior temporal cortex, which corresponds to the low level feature, the proposed BIHM adds two more layers upon the conventional framework to simulate inferotemporal cortex, exploring higher level feature invariance and selectivity. Furthermore, we firstly utilize the BIHM in the image recommendation. To demonstrate the effectiveness of proposed model, we use it to image classification and retrieval tasks and perform experiments on CalTech5, Imagenet and CalTech256 datasets. The experiment results show that BIHM exhibits better performance than the conventional model in the tasks and is very comparable to existing architectures.
WOS关键词ORTHOGONAL MATCHING PURSUIT ; OBJECT RECOGNITION ; RECEPTIVE FIELDS ; RETRIEVAL ; FEATURES ; CORTEX ; SCENE
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000425296500016
资助机构National Science Foundation of China(61603389) ; National Natural Science Foundation of China(61502494 ; Strategic Priority Research Program of the CAS(XDB02080003) ; Development of Science and Technology of Guangdong Province Special Fund Project(2016B090910001) ; 61210009)
源URL[http://ir.ia.ac.cn/handle/173211/15332]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组
作者单位1.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China
3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai, Peoples R China
4.Nanchang Univ, Sch Informat Engn, Nanchang, Jiangxi, Peoples R China
推荐引用方式
GB/T 7714		 Lu, Yan-Feng,Qiao, Hong,Li, Yi,et al. Image recommendation based on a novel biologically inspired hierarchical model[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2018,77(4):4323-4337.
APA Lu, Yan-Feng,Qiao, Hong,Li, Yi,&Jia, Li-Hao.(2018).Image recommendation based on a novel biologically inspired hierarchical model.MULTIMEDIA TOOLS AND APPLICATIONS,77(4),4323-4337.
MLA Lu, Yan-Feng,et al."Image recommendation based on a novel biologically inspired hierarchical model".MULTIMEDIA TOOLS AND APPLICATIONS 77.4(2018):4323-4337.

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。