Incomplete Cross-modal Retrieval with Dual-Aligned Variational Autoencoders

模式 计算机科学 杠杆(统计) 人工智能 模态(人机交互) 情态动词 对偶(语法数字) 机器学习 自然语言处理 模式识别(心理学) 社会科学 文学类 艺术 社会学 化学 高分子化学
作者
Mengmeng Jing,Jingjing Li,Lei Zhu,Ke Lü,Yang Yang,Zi Huang
标识
DOI:10.1145/3394171.3413676
摘要

Learning the relationship between the multi-modal data, e.g., texts, images and videos, is a classic task in the multimedia community. Cross-modal retrieval (CMR) is a typical example where the query and the corresponding results are in different modalities. Yet, a majority of existing works investigate CMR with an ideal assumption that the training samples in every modality are sufficient and complete. In real-world applications, however, this assumption does not always hold. Mismatch is common in multi-modal datasets. There is a high chance that samples in some modalities are either missing or corrupted. As a result, incomplete CMR has become a challenging issue. In this paper, we propose a Dual-Aligned Variational Autoencoders (DAVAE) to address the incomplete CMR problem. Specifically, we propose to learn modality-invariant representations for different modalities and use the learned representations for retrieval. We train multiple autoencoders, one for each modality, to learn the latent factors among different modalities. These latent representations are further dual-aligned at the distribution level and the semantic level to alleviate the modality gaps and enhance the discriminability of representations. For missing instances, we leverage generative models to synthesize latent representations for them. Notably, we test our method with different ratios of random incompleteness.Extensive experiments on three datasets verify that our method can consistently outperform the state-of-the-arts.
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
万能图书馆应助多多采纳,获得10
1秒前
风起完成签到 ,获得积分10
1秒前
wwwwww完成签到,获得积分10
1秒前
量子星尘发布了新的文献求助10
2秒前
无花果应助好好采纳,获得10
2秒前
2秒前
xyx945应助创新采纳,获得10
4秒前
5秒前
6秒前
情怀应助madefu采纳,获得10
7秒前
whatever应助arrebol采纳,获得10
8秒前
秦羽发布了新的文献求助10
8秒前
专注的乐荷完成签到,获得积分20
8秒前
超级飞侠应助YYYZZX1采纳,获得10
9秒前
10秒前
11秒前
Yanz完成签到,获得积分10
12秒前
12秒前
13秒前
善良的非笑完成签到,获得积分10
15秒前
15秒前
小二郎应助jiabaoyu采纳,获得10
15秒前
无奈秋荷发布了新的文献求助10
16秒前
17秒前
黄哈哈发布了新的文献求助10
18秒前
多多发布了新的文献求助10
18秒前
20秒前
李健的小迷弟应助Brian采纳,获得10
20秒前
20秒前
20秒前
liujian完成签到,获得积分10
21秒前
21秒前
脑洞疼应助wl301采纳,获得20
22秒前
22秒前
早安发布了新的文献求助10
22秒前
顾矜应助小岚花采纳,获得10
22秒前
23秒前
24秒前
24秒前
242588发布了新的文献求助10
24秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3988827
求助须知:如何正确求助?哪些是违规求助? 3531197
关于积分的说明 11252739
捐赠科研通 3269830
什么是DOI,文献DOI怎么找? 1804815
邀请新用户注册赠送积分活动 881915
科研通“疑难数据库(出版商)”最低求助积分说明 809028