首页|期刊导航|智能科学与技术学报|基于集成学习与聚类联合标注的多模态个体情绪识别

基于集成学习与聚类联合标注的多模态个体情绪识别OACSTPCD

Multimodal individual emotion recognition with joint labeling based on integrated learning and clustering

中文摘要英文摘要

针对通用情绪识别模型面对不同个体时的低识别精度问题,提出一种基于集成学习与聚类联合标注的多模态个体情绪识别方法.该方法首先基于公共数据集训练通用情绪识别模型,然后分析公共数据集数据与个体无标签数据的分布差异,建立跨域模型来预测和标注个体数据的伪标签.同时,对个体数据进行加权聚类并标注聚类标签,利用聚类标签与伪标签进行联合标注,筛选高置信度样本进一步训练通用模型,得到个性化情绪识别模型.实验采集3名被试的3种情绪数据并使用该方法标注,最后优化得到的…查看全部>>

To address the low recognition accuracy of generic emotion recognition models when faced with different indi-viduals,a multimodal individual emotion recognition technique based on joint labelling with integrated learning and clus-tering was proposed.The method first trained a generic emotion recognition model based on a public dataset,then anal-lysed the distributional differences between the data in the public dataset and the unlabelled data of individuals,…查看全部>>

柯善军;聂成洋;王钰苗;何邦胜

重庆理工大学车辆工程学院,重庆 400050重庆理工大学车辆工程学院,重庆 400050重庆理工大学车辆工程学院,重庆 400050重庆理工大学车辆工程学院,重庆 400050

计算机与自动化

个体情绪识别领域自适应集成学习聚类联合标注

individual emotion recognitiondomain adaptationintegrated learningclusteringjoint annotation

《智能科学与技术学报》 2024 (1)

76-87,12

重庆市教委科学技术研究项目(No.2020CJZ053)The Scientific and Technological Research Program of Chongqing Municipal Education Commission(No.2020CJZ053)

10.11959/j.issn.2096-6652.202401

评论

您当前未登录!去登录点击加载更多...