用于图像文本匹配的新型跨维粗粒度互补网络。

IF 3.5 4区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
PeerJ Computer Science Pub Date : 2025-03-03 eCollection Date: 2025-01-01 DOI:10.7717/peerj-cs.2725
Meizhen Liu, Anis Salwa Mohd Khairuddin, Khairunnisa Hasikin, Weitong Liu
{"title":"用于图像文本匹配的新型跨维粗粒度互补网络。","authors":"Meizhen Liu, Anis Salwa Mohd Khairuddin, Khairunnisa Hasikin, Weitong Liu","doi":"10.7717/peerj-cs.2725","DOIUrl":null,"url":null,"abstract":"<p><p>The fundamental aspects of multimodal applications such as image-text matching, and cross-modal heterogeneity gap between images and texts have always been challenging and complex. Researchers strive to overcome the challenges by proposing numerous significant efforts directed toward narrowing the semantic gap between visual and textual modalities. However, existing methods are usually limited to computing the similarity between images (image regions) and text (text words), ignoring the semantic consistency between fine-grained matching of word regions and coarse-grained overall matching of image and text. Additionally, these methods often ignore the semantic differences across different feature dimensions. Such limitations may result in an overemphasis on specific details at the expense of holistic understanding during image-text matching. To tackle this challenge, this article proposes a new Cross-Dimensional Coarse-Fine-Grained Complementary Network (CDGCN). Firstly, the proposed CDGCN performs fine-grained semantic alignment of image regions and sentence words based on cross-dimensional dependencies. Next, a Coarse-Grained Cross-Dimensional Semantic Aggregation module (CGDSA) is developed to complement local alignment with global image-text matching ensuring semantic consistency. This module aggregates local features across different dimensions as well as within the same dimension to form coherent global features, thus preserving the semantic integrity of the information. The proposed CDGCN is evaluated on two multimodal datasets, Flickr30K and MS-COCO against state-of-the-art methods. The proposed CDGCN achieved substantial improvements with performance increment of 7.7-16% for both datasets.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2725"},"PeriodicalIF":3.5000,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888920/pdf/","citationCount":"0","resultStr":"{\"title\":\"Novel cross-dimensional coarse-fine-grained complementary network for image-text matching.\",\"authors\":\"Meizhen Liu, Anis Salwa Mohd Khairuddin, Khairunnisa Hasikin, Weitong Liu\",\"doi\":\"10.7717/peerj-cs.2725\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>The fundamental aspects of multimodal applications such as image-text matching, and cross-modal heterogeneity gap between images and texts have always been challenging and complex. Researchers strive to overcome the challenges by proposing numerous significant efforts directed toward narrowing the semantic gap between visual and textual modalities. However, existing methods are usually limited to computing the similarity between images (image regions) and text (text words), ignoring the semantic consistency between fine-grained matching of word regions and coarse-grained overall matching of image and text. Additionally, these methods often ignore the semantic differences across different feature dimensions. Such limitations may result in an overemphasis on specific details at the expense of holistic understanding during image-text matching. To tackle this challenge, this article proposes a new Cross-Dimensional Coarse-Fine-Grained Complementary Network (CDGCN). Firstly, the proposed CDGCN performs fine-grained semantic alignment of image regions and sentence words based on cross-dimensional dependencies. Next, a Coarse-Grained Cross-Dimensional Semantic Aggregation module (CGDSA) is developed to complement local alignment with global image-text matching ensuring semantic consistency. This module aggregates local features across different dimensions as well as within the same dimension to form coherent global features, thus preserving the semantic integrity of the information. The proposed CDGCN is evaluated on two multimodal datasets, Flickr30K and MS-COCO against state-of-the-art methods. The proposed CDGCN achieved substantial improvements with performance increment of 7.7-16% for both datasets.</p>\",\"PeriodicalId\":54224,\"journal\":{\"name\":\"PeerJ Computer Science\",\"volume\":\"11 \",\"pages\":\"e2725\"},\"PeriodicalIF\":3.5000,\"publicationDate\":\"2025-03-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888920/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"PeerJ Computer Science\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.7717/peerj-cs.2725\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"PeerJ Computer Science","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.7717/peerj-cs.2725","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

本文章由计算机程序翻译,如有差异,请以英文原文为准。
Novel cross-dimensional coarse-fine-grained complementary network for image-text matching.

The fundamental aspects of multimodal applications such as image-text matching, and cross-modal heterogeneity gap between images and texts have always been challenging and complex. Researchers strive to overcome the challenges by proposing numerous significant efforts directed toward narrowing the semantic gap between visual and textual modalities. However, existing methods are usually limited to computing the similarity between images (image regions) and text (text words), ignoring the semantic consistency between fine-grained matching of word regions and coarse-grained overall matching of image and text. Additionally, these methods often ignore the semantic differences across different feature dimensions. Such limitations may result in an overemphasis on specific details at the expense of holistic understanding during image-text matching. To tackle this challenge, this article proposes a new Cross-Dimensional Coarse-Fine-Grained Complementary Network (CDGCN). Firstly, the proposed CDGCN performs fine-grained semantic alignment of image regions and sentence words based on cross-dimensional dependencies. Next, a Coarse-Grained Cross-Dimensional Semantic Aggregation module (CGDSA) is developed to complement local alignment with global image-text matching ensuring semantic consistency. This module aggregates local features across different dimensions as well as within the same dimension to form coherent global features, thus preserving the semantic integrity of the information. The proposed CDGCN is evaluated on two multimodal datasets, Flickr30K and MS-COCO against state-of-the-art methods. The proposed CDGCN achieved substantial improvements with performance increment of 7.7-16% for both datasets.

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
PeerJ Computer Science
PeerJ Computer Science Computer Science-General Computer Science
CiteScore
6.10
自引率
5.30%
发文量
332
审稿时长
10 weeks
期刊介绍: PeerJ Computer Science is the new open access journal covering all subject areas in computer science, with the backing of a prestigious advisory board and more than 300 academic editors.
×
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