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

计算机科学 情报检索 嵌入 自然语言处理 图像(数学) 文字嵌入 人工智能 关系(数据库) 数据挖掘
作者
Duoduo Feng,Xiangteng He,Yuxin Peng
出处
期刊:ACM Transactions on Multimedia Computing, Communications, and Applications [Association for Computing Machinery]
卷期号:19 (5): 1-21 被引量:13
标识
DOI:10.1145/3580501
摘要

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 .
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
3秒前
3秒前
chi发布了新的文献求助20
4秒前
5秒前
上官若男应助cx采纳,获得10
7秒前
天真玲发布了新的文献求助10
7秒前
贺知什么书完成签到,获得积分10
7秒前
9秒前
11秒前
十点睡六点起完成签到,获得积分10
12秒前
传奇3应助滴滴滴采纳,获得10
12秒前
WEIWEI发布了新的文献求助10
14秒前
风趣绝施完成签到,获得积分20
14秒前
REnewbie发布了新的文献求助10
14秒前
稳重书双完成签到,获得积分10
14秒前
catsfat发布了新的文献求助10
16秒前
16秒前
katchulailai完成签到,获得积分10
17秒前
20秒前
20秒前
21秒前
ffw1完成签到,获得积分10
23秒前
田様应助科研通管家采纳,获得10
24秒前
丘比特应助科研通管家采纳,获得10
24秒前
丘比特应助科研通管家采纳,获得10
25秒前
华仔应助科研通管家采纳,获得10
25秒前
xiaoxin完成签到,获得积分10
26秒前
天天快乐应助科研通管家采纳,获得10
26秒前
Virgil完成签到,获得积分10
26秒前
Hello应助曾经阁采纳,获得10
26秒前
26秒前
11完成签到,获得积分10
27秒前
文龙发布了新的文献求助10
27秒前
27秒前
汉堡包应助科研通管家采纳,获得10
27秒前
CipherSage应助科研通管家采纳,获得10
28秒前
Akim应助科研通管家采纳,获得10
28秒前
无私追命发布了新的文献求助10
28秒前
29秒前
haihe发布了新的文献求助20
29秒前
高分求助中
Impact of Mitophagy-Related Genes on the Diagnosis and Development of Esophageal Squamous Cell Carcinoma via Single-Cell RNA-seq Analysis and Machine Learning Algorithms 2000
Evolution 1500
How to Create Beauty: De Lairesse on the Theory and Practice of Making Art 1000
Gerard de Lairesse : an artist between stage and studio 670
CLSI EP47 Evaluation of Reagent Carryover Effects on Test Results, 1st Edition 550
Sport, Music, Identities 500
T/CAB 0344-2024 重组人源化胶原蛋白内毒素去除方法 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 2986949
求助须知:如何正确求助?哪些是违规求助? 2647826
关于积分的说明 7153129
捐赠科研通 2281735
什么是DOI,文献DOI怎么找? 1210092
版权声明 592408
科研通“疑难数据库(出版商)”最低求助积分说明 590961