Knowledge Commons of Institute of Automation,CAS
Semi-supervised Deep Generative Modelling of Incomplete Multi-Modality Emotional Data | |
Du Changde1,2; Du Changying3; Wang Hao3; Li Jinpeng1,2; Zheng Wei-Long4; Lu Bao-Liang4; He Huiguang1,2,5 | |
2018 | |
会议名称 | ACM Multimedia Conference |
会议日期 | October 22--26, 2018 |
会议地点 | Seoul, Republic of Korea |
摘要 | There are threefold challenges in emotion recognition. First, it is difficult to recognize human's emotional states only considering a single modality. Second, it is expensive to manually annotate the emotional data. Third, emotional data often suffers from missing modalities due to unforeseeable sensor malfunction or configuration issues. In this paper, we address all these problems under a novel multi-view deep generative framework. Specifically, we propose to model the statistical relationships of multi-modality emotional data using multiple modality-specific generative networks with a shared latent space. By imposing a Gaussian mixture assumption on the posterior approximation of the shared latent variables, our framework can learn the joint deep representation from multiple modalities and evaluate the importance of each modality simultaneously. To solve the labeled-data-scarcity problem, we extend our multi-view model to semi-supervised learning scenario by casting the semi-supervised classification problem as a specialized missing data imputation task. To address the missing-modality problem, we further extend our semi-supervised multi-view model to deal with incomplete data, where a missing view is treated as a latent variable and integrated out during inference. This way, the proposed overall framework can utilize all available (both labeled and unlabeled, as well as both complete and incomplete) data to improve its generalization ability. The experiments conducted on two real multi-modal emotion datasets demonstrated the superiority of our framework. |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23626 |
专题 | 脑图谱与类脑智能实验室_神经计算与脑机交互 |
通讯作者 | He Huiguang |
作者单位 | 1.Research Center for Brain-Inspired Intelligence \& NLPR, CASIA, Beijing 100190, China 2.University of Chinese Academy of Sciences, Beijing 100049, China 3.360 Search Lab, Beijing, China 4.Department of Computer Science and Engineering, SJTU, Shanghai, Beijing 5.Center for Excellence in Brain Science and Intelligence Technology, CAS, Beijing, China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Du Changde,Du Changying,Wang Hao,et al. Semi-supervised Deep Generative Modelling of Incomplete Multi-Modality Emotional Data[C],2018. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
ACMMM_2018_Semi-supe(1217KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论