亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Multi-Modal Transformer with Global-Local Alignment for Composed Query Image Retrieval

计算机科学 图像检索 嵌入 变压器 人工智能 查询扩展 编码器 模式识别(心理学) 计算机视觉 图像(数学) 情报检索 物理 量子力学 电压 操作系统
作者
Yahui Xu,Yi Bin,Jiwei Wei,Yang Yang,Guoqing Wang,Heng Tao Shen
出处
期刊:IEEE Transactions on Multimedia [Institute of Electrical and Electronics Engineers]
卷期号:25: 8346-8357 被引量:15
标识
DOI:10.1109/tmm.2023.3235495
摘要

In this paper, we study the composed query image retrieval, which aims at retrieving the target image similar to the composed query, i.e., a reference image and the desired modification text. Compared with conventional image retrieval, this task is more challenging as it not only requires precisely aligning the composed query and target image in a common embedding space, but also simultaneously extracting related information from the reference image and modification text. In order to properly extract related information from the composed query, existing methods usually embed vision-language inputs using different feature encoders, e.g., CNN for images and LSTM/BERT for text, and then employ a complicated manually-designed composition module for learning the joint image-text representation. However, the architecture discrepancy in feature encoders would restrict the vision-language plenitudinous interaction. Meanwhile, certain complicated composition designs might significantly hamper the generalization ability of the model. To tackle these problems, we propose a new framework termed ComqueryFormer, which effectively processes the composed query with the Transformer for this task. Specifically, to eliminate the architecture discrepancy, we leverage a unified transformer-based architecture to homogeneously encode the vision-language inputs. Meanwhile, instead of the complicated composition module, the neat yet effective cross-modal transformer is adopted to hierarchically fuse the composed query at various vision scales. On the other hand, we introduce an efficient global-local alignment module to narrow the distance between the composed query and the target image. It not only considers the divergence in the global joint embedding space but also forces the model to focus on the local detail differences. Extensive experiments on three real-world datasets demonstrate the superiority of our ComqueryFormer. Our code can be found at: https://github.com/uestc-xyh/ComqueryFormer .
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
畜牧笑笑完成签到 ,获得积分20
2秒前
斯文败类应助背后梦安采纳,获得10
5秒前
14秒前
背后梦安发布了新的文献求助10
20秒前
wang完成签到,获得积分10
39秒前
情怀应助Hermionezj采纳,获得10
41秒前
44秒前
47秒前
zqq完成签到,获得积分0
51秒前
三木发布了新的文献求助10
52秒前
量子星尘发布了新的文献求助10
52秒前
情怀应助三木采纳,获得10
1分钟前
猪猪发布了新的文献求助10
1分钟前
1分钟前
Hermionezj发布了新的文献求助10
1分钟前
善学以致用应助章鱼采纳,获得10
1分钟前
1分钟前
星辰大海应助科研通管家采纳,获得30
1分钟前
科研通AI2S应助科研通管家采纳,获得10
1分钟前
jyy应助科研通管家采纳,获得10
1分钟前
1分钟前
1分钟前
2分钟前
章鱼发布了新的文献求助10
2分钟前
2分钟前
2分钟前
2分钟前
量子星尘发布了新的文献求助10
2分钟前
mellow完成签到,获得积分10
2分钟前
2分钟前
两袖清风完成签到 ,获得积分10
2分钟前
甜甜发布了新的文献求助10
2分钟前
2分钟前
芋泥面包发布了新的文献求助10
2分钟前
甜甜完成签到,获得积分10
2分钟前
顾矜应助芋泥面包采纳,获得10
3分钟前
猪猪发布了新的文献求助10
3分钟前
3分钟前
量子星尘发布了新的文献求助10
3分钟前
芋泥面包发布了新的文献求助10
3分钟前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Immigrant Incorporation in East Asian Democracies 600
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3972762
求助须知:如何正确求助?哪些是违规求助? 3517085
关于积分的说明 11186142
捐赠科研通 3252538
什么是DOI,文献DOI怎么找? 1796527
邀请新用户注册赠送积分活动 876487
科研通“疑难数据库(出版商)”最低求助积分说明 805652