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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Learning Multifunctional Binary Codes for Personalized Image Retrieval

文献类型：期刊论文

作者Liu, Haomiao1,2,3; Wang, Ruiping1,2; Shan, Shiguang1,2; Chen, Xilin1,2
刊名INTERNATIONAL JOURNAL OF COMPUTER VISION
出版日期2020-03-17
页码20
关键词Image retrieval Multi-task learning Hashing
ISSN号0920-5691
DOI10.1007/s11263-020-01315-0
英文摘要Due to the highly complex semantic information of images, even with the same query image, the expected content-based image retrieval results could be very different and personalized in different scenarios. However, most existing hashing methods only preserve one single type of semantic similarity, making them incapable of addressing such realistic retrieval tasks. To deal with this problem, we propose a unified hashing framework to encode multiple types of information into the binary codes by exploiting convolutional networks (CNNs). Specifically, we assume that typical retrieval tasks are generally defined in two aspects, i.e. high-level semantics (e.g. object categories) and visual attributes (e.g. object shape and color). To this end, our Dual Purpose Hashing model is trained to jointly preserve two kinds of similarities characterizing the two aspects respectively. Moreover, since images with both category and attribute labels are scarce, our model is carefully designed to leverage the abundant partially labelled data as training inputs to alleviate the risk of overfitting. With such a framework, the binary codes of new-coming images can be readily obtained by quantizing the outputs of a specific CNN layer, and different retrieval tasks can be achieved by using the binary codes in different ways. Experiments on two large-scale datasets show that our method achieves comparable or even better performance than those state-of-the-art methods specifically designed for each individual retrieval task while being more compact than the compared methods.
资助项目973 Program[2015CB351802] ; Natural Science Foundation of China[61390511] ; Natural Science Foundation of China[61772500] ; CAS[QYZDJ-SSWJSC009] ; Youth Innovation Promotion Association[2015085]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000520662000005
出版者SPRINGER
源URL[http://119.78.100.204/handle/2XEOYT63/14088]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Wang, Ruiping
作者单位1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Huawei EI Innovat Lab, Beijing 100085, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Haomiao,Wang, Ruiping,Shan, Shiguang,et al. Learning Multifunctional Binary Codes for Personalized Image Retrieval[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2020:20.
APA Liu, Haomiao,Wang, Ruiping,Shan, Shiguang,&Chen, Xilin.(2020).Learning Multifunctional Binary Codes for Personalized Image Retrieval.INTERNATIONAL JOURNAL OF COMPUTER VISION,20.
MLA Liu, Haomiao,et al."Learning Multifunctional Binary Codes for Personalized Image Retrieval".INTERNATIONAL JOURNAL OF COMPUTER VISION (2020):20.

入库方式： OAI收割

来源：计算技术研究所

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。