基于相似矩阵池化的多指标融合图像检索

Xin Chen, Jun Wu, Shaoyan Sun, Q. Tian
{"title":"基于相似矩阵池化的多指标融合图像检索","authors":"Xin Chen, Jun Wu, Shaoyan Sun, Q. Tian","doi":"10.1109/ICC.2017.7996333","DOIUrl":null,"url":null,"abstract":"Different kinds of features hold some distinct merits, making them complementary to each other. Inspired by this idea an index level multiple feature fusion scheme via similarity matrix pooling is proposed in this paper. We first compute the similarity matrix of each index, and then a novel scheme is used to pool on these similarity matrices for updating the original indices. Compared with the existing fusion schemes, the proposed scheme performs feature fusion at index level to save memory and reduce computational complexity. On the other hand, the proposed scheme treats different kinds of features adaptively based on its importance, thus improves retrieval accuracy. The performance of the proposed approach is evaluated using two public datasets, which significantly outperforms the baseline methods in retrieval accuracy with low memory consumption and computational complexity.","PeriodicalId":6517,"journal":{"name":"2017 IEEE International Conference on Communications (ICC)","volume":"45 1","pages":"1-6"},"PeriodicalIF":0.0000,"publicationDate":"2017-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Multi-index fusion via similarity matrix pooling for image retrieval\",\"authors\":\"Xin Chen, Jun Wu, Shaoyan Sun, Q. Tian\",\"doi\":\"10.1109/ICC.2017.7996333\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Different kinds of features hold some distinct merits, making them complementary to each other. Inspired by this idea an index level multiple feature fusion scheme via similarity matrix pooling is proposed in this paper. We first compute the similarity matrix of each index, and then a novel scheme is used to pool on these similarity matrices for updating the original indices. Compared with the existing fusion schemes, the proposed scheme performs feature fusion at index level to save memory and reduce computational complexity. On the other hand, the proposed scheme treats different kinds of features adaptively based on its importance, thus improves retrieval accuracy. The performance of the proposed approach is evaluated using two public datasets, which significantly outperforms the baseline methods in retrieval accuracy with low memory consumption and computational complexity.\",\"PeriodicalId\":6517,\"journal\":{\"name\":\"2017 IEEE International Conference on Communications (ICC)\",\"volume\":\"45 1\",\"pages\":\"1-6\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-05-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 IEEE International Conference on Communications (ICC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICC.2017.7996333\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE International Conference on Communications (ICC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICC.2017.7996333","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

摘要

不同的特征各有优点,相互补充。受此思想的启发,本文提出了一种基于相似矩阵池化的索引级多特征融合方案。首先计算每个索引的相似度矩阵,然后采用一种新的方法对这些相似度矩阵进行池化,从而更新原始索引。与现有融合方案相比,该方案在索引级进行特征融合,节省内存,降低计算复杂度。另一方面,该方案根据特征的重要性自适应处理不同类型的特征,从而提高了检索精度。使用两个公共数据集对该方法的性能进行了评估,结果表明该方法在检索精度上明显优于基线方法,并且具有较低的内存消耗和计算复杂度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Multi-index fusion via similarity matrix pooling for image retrieval
Different kinds of features hold some distinct merits, making them complementary to each other. Inspired by this idea an index level multiple feature fusion scheme via similarity matrix pooling is proposed in this paper. We first compute the similarity matrix of each index, and then a novel scheme is used to pool on these similarity matrices for updating the original indices. Compared with the existing fusion schemes, the proposed scheme performs feature fusion at index level to save memory and reduce computational complexity. On the other hand, the proposed scheme treats different kinds of features adaptively based on its importance, thus improves retrieval accuracy. The performance of the proposed approach is evaluated using two public datasets, which significantly outperforms the baseline methods in retrieval accuracy with low memory consumption and computational complexity.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信