Enhancing multimodal depression detection with intra- and inter-sample contrastive learning

判别式 计算机科学 样品(材料) 人工智能 模态(人机交互) 特征(语言学) 机器学习 班级(哲学) 利用 采样(信号处理) 模式识别(心理学) 自然语言处理 语言学 计算机视觉 哲学 化学 滤波器(信号处理) 色谱法 计算机安全
作者
Meiling Li,Yuting Wei,Yangfu Zhu,Siqi Wei,Bin Wu
出处
期刊:Information Sciences [Elsevier BV]
卷期号:684: 121282-121282 被引量:11
标识
DOI:10.1016/j.ins.2024.121282
摘要

Multimodal depression detection (MDD) has garnered significant interest in recent years. Current methods typically integrate multimodal information within samples to distinguish positive from negative samples, but they often neglect the relationships between samples. Despite similarities within the same class, individual variations exist. By leveraging these relationships, we can provide supervision signals for both inter- and intra-class samples, thereby enhancing the discriminative power of user representations. Inspired by this observation, we introduce IISFD, a novel approach that concurrently exploits intra-sample contrastive learning and inter-sample contrastive learning with hard negative sampling. This method comprehensively considers information both within individual samples and across samples. Specifically, we decompose the multimodal inputs of each sample, including audio, vision and text, into modality-common features and modality-specific features. To obtain better decomposed feature representations, we integrate intra-sample contrastive learning and inter-sample contrastive learning with hard negative sampling. Additionally, detailed modal information is obtained through unimodal reconstruction. By passing the decomposed features through a carefully designed multimodal fusion module, we obtain more discriminative user representations. Experimental results on two publicly available datasets demonstrate the superiority of our model, highlighting its effectiveness in leveraging both intra- and inter-sample information for enhanced MDD.
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
Charon发布了新的文献求助30
刚刚
科研通AI6.2的应助被wuhuhu采纳,获得10
1秒前
04d的应助被wuhuhu采纳,获得10
1秒前
朱博发布了新的文献求助10
1秒前
蓝天的应助被wuhuhu采纳,获得10
1秒前
CipherSage的应助被wuhuhu采纳,获得10
1秒前
斯文败类的应助被小黄鸭采纳,获得10
1秒前
搞怪的老九的应助被wuhuhu采纳,获得10
1秒前
成步堂龙一完成签到,获得积分10
1秒前
NexusExplorer的应助被wuhuhu采纳,获得10
2秒前
awwwww的应助被wuhuhu采纳,获得10
2秒前
高文昕完成签到,获得积分10
2秒前
宁一样发布了新的文献求助10
2秒前
搞怪的老九的应助被wuhuhu采纳,获得10
2秒前
搞怪的老九的应助被wuhuhu采纳,获得10
2秒前
搞怪的老九的应助被wuhuhu采纳,获得10
2秒前
xxxie发布了新的文献求助10
2秒前
3秒前
sci发布了新的文献求助10
3秒前
orixero的应助被ECCE采纳,获得10
3秒前
4秒前
大模型的应助被WBH36323采纳,获得10
4秒前
4秒前
4秒前
5秒前
机智的皮皮虾的应助被摸鱼仔采纳,获得10
5秒前
Lyh完成签到,获得积分10
5秒前
5秒前
sakiko_togawa完成签到,获得积分10
5秒前
5秒前
5秒前
5秒前
6秒前
zhm的应助被任善良采纳,获得10
6秒前
6秒前
乖乖完成签到,获得积分10
7秒前
RenJL完成签到,获得积分10
7秒前
7秒前
7秒前
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
John McDowells Bildungstheorie 800
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
Handbook of Pharmaceutical Excipients. 9th ed 400
Synthesis, Application and Future Perspectives of Smart Nano-materials - Part 1 400
Breaking the World 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8155737
求助须知:如何正确求助?哪些是违规求助? 9552018
关于积分的说明 21707687
捐赠科研通 7744923
什么是DOI,文献DOI怎么找? 3426177
关于科研通互助平台的介绍 2551229
邀请新用户注册赠送积分活动 2469949