• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

一种用于图建模集合可达性分析的多方面方法。

A faceted approach to reachability analysis of graph modelled collections.

作者信息

Sabetghadam Serwah, Lupu Mihai, Bierig Ralf, Rauber Andreas

机构信息

1Institute of Software Technology and Interactive Systems, Vienna University of Technology, Vienna, Austria.

2Department of Computer Science, Maynooth University, Maynooth, Ireland.

出版信息

Int J Multimed Inf Retr. 2018;7(3):157-171. doi: 10.1007/s13735-017-0145-8. Epub 2017 Dec 16.

DOI:10.1007/s13735-017-0145-8
PMID:30956928
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC6417456/
Abstract

Nowadays, there is a proliferation of available information sources from different modalities-text, images, audio, video and more. Information objects are not isolated anymore. They are frequently connected via metadata, semantic links, etc. This leads to various challenges in graph-based information retrieval. This paper is concerned with the reachability analysis of multimodal graph modelled collections. We use our framework to leverage the combination of features of different modalities through our formulation of faceted search. This study highlights the effect of different facets and link types in improving reachability of relevant information objects. The experiments are performed on the Image CLEF 2011 Wikipedia collection with about 400,000 documents and images. The results demonstrate that the combination of different facets is conductive to obtain higher reachability. We obtain 373% recall gain for very hard topics by using our graph model of the collection. Further, by adding semantic links to the collection, we gain a 10% increase in the overall recall.

摘要

如今，来自不同形式（文本、图像、音频、视频等）的可用信息源大量涌现。信息对象不再孤立。它们常常通过元数据、语义链接等相互连接。这给基于图的信息检索带来了各种挑战。本文关注多模态图建模集合的可达性分析。我们通过构建分面搜索，利用我们的框架来整合不同模态的特征。本研究突出了不同分面和链接类型在提高相关信息对象可达性方面的作用。实验是在拥有约40万份文档和图像的2011年图像CLEF维基百科集合上进行的。结果表明，不同分面的组合有助于获得更高的可达性。通过使用我们的集合图模型，对于非常难的主题，我们获得了373%的召回率提升。此外，通过向集合中添加语义链接，我们在总体召回率上提高了10%。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/92eb0f7dc249/13735_2017_145_Fig12_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/fe7d9a388d9c/13735_2017_145_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/a5390db7098f/13735_2017_145_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/8eca50575852/13735_2017_145_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/344c22ed30a3/13735_2017_145_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/80c7771dd7b2/13735_2017_145_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/bb9aa23ff8e5/13735_2017_145_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/d294bf258c30/13735_2017_145_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/24f37c94022f/13735_2017_145_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/b564444a6624/13735_2017_145_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/7a2766e4312c/13735_2017_145_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/35bd3864787d/13735_2017_145_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/92eb0f7dc249/13735_2017_145_Fig12_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/fe7d9a388d9c/13735_2017_145_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/a5390db7098f/13735_2017_145_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/8eca50575852/13735_2017_145_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/344c22ed30a3/13735_2017_145_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/80c7771dd7b2/13735_2017_145_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/bb9aa23ff8e5/13735_2017_145_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/d294bf258c30/13735_2017_145_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/24f37c94022f/13735_2017_145_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/b564444a6624/13735_2017_145_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/7a2766e4312c/13735_2017_145_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/35bd3864787d/13735_2017_145_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e209/6417456/92eb0f7dc249/13735_2017_145_Fig12_HTML.jpg

相似文献

1
A faceted approach to reachability analysis of graph modelled collections.一种用于图建模集合可达性分析的多方面方法。
Int J Multimed Inf Retr. 2018;7(3):157-171. doi: 10.1007/s13735-017-0145-8. Epub 2017 Dec 16.
2
An SUI-based approach to explore visual search results cluster-graphs.基于 SUI 的方法探索视觉搜索结果聚类图。
PLoS One. 2023 Jan 20;18(1):e0280400. doi: 10.1371/journal.pone.0280400. eCollection 2023.
3
FacetGist: Collective Extraction of Document Facets in Large Technical Corpora.方面要点：大型技术语料库中文档方面的集体提取
Proc ACM Int Conf Inf Knowl Manag. 2016 Oct;2016:871-880. doi: 10.1145/2983323.2983828.
4
Design of Knowledge Graph Retrieval System for Legal and Regulatory Framework of Multilevel Latent Semantic Indexing.多层面潜在语义索引法律和监管框架的知识图检索系统设计。
Comput Intell Neurosci. 2022 Jul 19;2022:6781043. doi: 10.1155/2022/6781043. eCollection 2022.
5
An efficient reachability query based pruning algorithm in e-health scenario.电子健康场景中的一种高效可达性查询剪枝算法。
J Biomed Inform. 2019 Jun;94:103171. doi: 10.1016/j.jbi.2019.103171. Epub 2019 Apr 18.
6
A graph-based approach for the retrieval of multi-modality medical images.基于图的多模态医学图像检索方法。
Med Image Anal. 2014 Feb;18(2):330-42. doi: 10.1016/j.media.2013.11.003. Epub 2013 Dec 6.
7
Document/query expansion based on selecting significant concepts for context based retrieval of medical images.基于选择显著概念的文档/查询扩展，用于基于上下文的医学图像检索。
J Biomed Inform. 2019 Jul;95:103210. doi: 10.1016/j.jbi.2019.103210. Epub 2019 May 17.
8
A new design of multimedia big data retrieval enabled by deep feature learning and Adaptive Semantic Similarity Function.一种由深度特征学习和自适应语义相似性函数实现的多媒体大数据检索新设计。
Multimed Syst. 2022;28(3):1039-1058. doi: 10.1007/s00530-022-00897-8. Epub 2022 Feb 5.
9
[A retrieval method of drug molecules based on graph collapsing].基于图折叠的药物分子检索方法
Beijing Da Xue Xue Bao Yi Xue Ban. 2018 Apr 18;50(2):368-374.
10
MedGraph: A semantic biomedical information retrieval framework using knowledge graph embedding for PubMed.MedGraph：一种使用知识图谱嵌入技术进行PubMed语义生物医学信息检索的框架。
Front Big Data. 2022 Oct 19;5:965619. doi: 10.3389/fdata.2022.965619. eCollection 2022.

本文引用的文献

1
Multimodal graph-based reranking for web image search.基于多模态图的网页图像搜索重新排序。
IEEE Trans Image Process. 2012 Nov;21(11):4649-61. doi: 10.1109/TIP.2012.2207397. Epub 2012 Jul 17.
2
Improving Web image search by bag-based reranking.基于包的重新排序改进网络图像搜索。
IEEE Trans Image Process. 2011 Nov;20(11):3280-90. doi: 10.1109/TIP.2011.2159227. Epub 2011 Jun 9.
3
VisualRank: applying PageRank to large-scale image search.视觉排名：将网页排名应用于大规模图像搜索。
IEEE Trans Pattern Anal Mach Intell. 2008 Nov;30(11):1877-90. doi: 10.1109/TPAMI.2008.121.