Advanced Multimodal Deep Learning Architecture for Image-Text Matching

建筑 匹配(统计) 计算机科学 深度学习 人工智能 图像(数学) 自然语言处理 计算机体系结构 艺术 数学 统计 视觉艺术
作者
Jinyin Wang,Hai‐Jing Zhang,Yihao Zhong,Yingbin Liang,Rongwei Ji,Yiru Cang
出处
期刊:Cornell University - arXiv
标识
DOI:10.48550/arxiv.2406.15306
摘要

Image-text matching is a key multimodal task that aims to model the semantic association between images and text as a matching relationship. With the advent of the multimedia information age, image, and text data show explosive growth, and how to accurately realize the efficient and accurate semantic correspondence between them has become the core issue of common concern in academia and industry. In this study, we delve into the limitations of current multimodal deep learning models in processing image-text pairing tasks. Therefore, we innovatively design an advanced multimodal deep learning architecture, which combines the high-level abstract representation ability of deep neural networks for visual information with the advantages of natural language processing models for text semantic understanding. By introducing a novel cross-modal attention mechanism and hierarchical feature fusion strategy, the model achieves deep fusion and two-way interaction between image and text feature space. In addition, we also optimize the training objectives and loss functions to ensure that the model can better map the potential association structure between images and text during the learning process. Experiments show that compared with existing image-text matching models, the optimized new model has significantly improved performance on a series of benchmark data sets. In addition, the new model also shows excellent generalization and robustness on large and diverse open scenario datasets and can maintain high matching performance even in the face of previously unseen complex situations.
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
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
2秒前
无花果应助专注寻菱采纳,获得10
5秒前
彭于晏应助小龚热心肠采纳,获得10
5秒前
tcmlida发布了新的文献求助30
6秒前
9秒前
大海的DOI完成签到 ,获得积分10
10秒前
12秒前
97发布了新的文献求助10
14秒前
15秒前
暴躁的访波完成签到,获得积分10
17秒前
无心的冰巧应助暴躁的访波采纳,获得200
20秒前
21秒前
笑点低的冬瓜应助yemiao采纳,获得10
21秒前
坦率道之发布了新的文献求助10
22秒前
23秒前
自由依秋应助Zoeee采纳,获得10
24秒前
Eric完成签到 ,获得积分10
25秒前
fancy完成签到 ,获得积分10
26秒前
立军发布了新的文献求助30
26秒前
负责的高烽完成签到,获得积分10
26秒前
自由依秋应助晴空万里采纳,获得10
27秒前
Ergou发布了新的文献求助10
27秒前
豆子发布了新的文献求助10
27秒前
27秒前
psycan完成签到,获得积分20
28秒前
28秒前
桃井尤川发布了新的文献求助10
32秒前
正直的迎丝完成签到 ,获得积分10
32秒前
33秒前
葫芦大王关注了科研通微信公众号
33秒前
tcmlida发布了新的文献求助30
36秒前
共享精神应助97采纳,获得10
36秒前
bkagyin应助傻呼呼采纳,获得10
36秒前
37秒前
今后应助Ergou采纳,获得10
37秒前
38秒前
song完成签到,获得积分10
38秒前
40秒前
ZHOU发布了新的文献求助10
40秒前
兼听则明发布了新的文献求助10
40秒前
高分求助中
Production Logging: Theoretical and Interpretive Elements 2500
Востребованный временем 2500
Hopemont Capacity Assessment Interview manual and scoring guide 1000
Classics in Total Synthesis IV: New Targets, Strategies, Methods 1000
Neuromuscular and Electrodiagnostic Medicine Board Review 700
Mantids of the euro-mediterranean area 600
Mantodea of the World: Species Catalog Andrew M 500
热门求助领域 (近24小时)
化学 医学 材料科学 生物 工程类 有机化学 生物化学 纳米技术 内科学 物理 化学工程 计算机科学 复合材料 基因 遗传学 物理化学 催化作用 细胞生物学 免疫学 电极
热门帖子
关注 科研通微信公众号,转发送积分 3441528
求助须知:如何正确求助?哪些是违规求助? 3038152
关于积分的说明 8970749
捐赠科研通 2726439
什么是DOI,文献DOI怎么找? 1495472
科研通“疑难数据库(出版商)”最低求助积分说明 691208
邀请新用户注册赠送积分活动 688232