MKVSE: Multimodal Knowledge Enhanced Visual-semantic Embedding for Image-text Retrieval

Author:

Feng Duoduo1ORCID,He Xiangteng1ORCID,Peng Yuxin2ORCID

Affiliation:

1. Peking University, Beijing, China

2. Peking University, China and Peng Cheng Laboratory, Shenzhen, China

Abstract

Image-text retrieval aims to take the text (image) query to retrieve the semantically relevant images (texts), which is fundamental and critical in the search system, online shopping, and social network. Existing works have shown the effectiveness of visual-semantic embedding and unimodal knowledge exploiting (e.g., textual knowledge) in connecting the image and text. However, they neglect the implicit multimodal knowledge relations between these two modalities when the image contains information that is not directly described in the text, hindering the ability to connect the image and text with the implicit semantic relations. For instance, an image shows a person next to the “tap” but the pairing text description may only include the word “wash,” missing the washing tool “tap.” The implicit semantic relation between image object “tap” and text word “wash” can help to connect the above image and text. To sufficiently utilize the implicit multimodal knowledge relations, we propose a M ultimodal K nowledge enhanced V isual- S emantic E mbedding (MKVSE) approach building a multimodal knowledge graph to explicitly represent the implicit multimodal knowledge relations and injecting it to visual-semantic embedding for image-text retrieval task. The contributions in this article can be summarized as follows: (1) M ultimodal K nowledge G raph (MKG) is proposed to explicitly represent the implicit multimodal knowledge relations between the image and text as intra-modal semantic relations and inter-modal co-occurrence relations . Intra-modal semantic relations provide synonymy information that is implicit in the unimodal data such as the text corpus. And inter-modal co-occurrence relations characterize the co-occurrence correlations (such as temporal, causal, and logical) that are implicit in image-text pairs. These two relations help establishing reliable image-text connections in the higher-level semantic space. (2) M ultimodal G raph C onvolution N etworks (MGCN) is proposed to reason on the MKG in two steps to sufficiently utilize the implicit multimodal knowledge relations. In the first step, MGCN focuses on the intra-modal relations to distinguish other entities in the semantic space. In the second step, MGCN focuses on the inter-modal relations to connect multimodal entities based on co-occurrence correlations. The two-step reasoning manner can sufficiently utilize the implicit semantic relations between two modal entities to enhance the embeddings of the image and text. Extensive experiments are conducted on two widely used datasets, namely, Flickr30k and MSCOCO, to demonstrate the superiority of the proposed MKVSE approach in achieving state-of-the-art performances. The codes are available at https://github.com/PKU-ICST-MIPL/MKVSE-TOMM2023 .

Funder

National Natural Science Foundation of China

2022 Tencent Wechat Rhino-Bird Focused Research Program

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Hardware and Architecture

Reference59 articles.

1. Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

2. Contextual Embeddings: When Are They Worth It?

3. Neural machine translation by jointly learning to align and translate;Bahdanau Dzmitry;arXiv preprint arXiv:1409.0473,2014

4. Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. O’Reilly Media, Inc.

5. Dawei Chen, Zhixu Li, Binbin Gu, and Zhigang Chen. 2021. Multimodal named entity recognition with image attributes and image knowledge. In Proceedings of the International Conference on Database Systems for Advanced Applications. Springer, 186–201.

Cited by 11 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Cross-modality interaction reasoning for enhancing vision-language pre-training in image-text retrieval;Applied Intelligence;2024-09-11

2. Hypercube Pooling for Visual Semantic Embedding;ACM Transactions on Multimedia Computing, Communications, and Applications;2024-08-23

3. Multi-view and region reasoning semantic enhancement for image-text retrieval;Multimedia Systems;2024-06-15

4. Semantic deep learning and adaptive clustering for handling multimodal multimedia information retrieval;Multimedia Tools and Applications;2024-05-25

5. Multimodal Knowledge Graph-Guided Cross-Modal Graph Network for Image-Text Retrieval;2024 IEEE International Conference on Big Data and Smart Computing (BigComp);2024-02-18

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3