Knowledge Commons of Institute of Automation,CAS
Doubly Semi-Supervised Multimodal Adversarial Learning for Classification, Generation and Retrieval | |
Du CD(杜长德)1; Du CY(杜长营)2; He HG(何晖光)1 | |
2019 | |
会议名称 | IEEE International Conference on Multimedia and Expo |
会议日期 | 2019/7/8 |
会议地点 | 上海 |
会议录编者/会议主办者 | IEEE |
摘要 | Learning over incomplete multi-modality data is a challenging problem with strong practical applications. Most existing multi-modal data imputation approaches have two limitations: (1) they are unable to accurately control the semantics of imputed modalities; and (2) without a shared low-dimensional latent space, they do not scale well with multiple modalities. To overcome the limitations, we propose a novel doubly semi-supervised multi-modal learning framework (DSML) with a modality-shared latent space and modality-specific generators, encoders and classifiers. We design novel softmax-based discriminators to train all modules adversarially. As a unified framework, DSML can be applied in multi-modal semi-supervised classification, missing modality imputation and fast cross-modality retrieval tasks simultaneously. Experiments on multiple datasets demonstrate its advantages. |
收录类别 | EI |
语种 | 英语 |
是否为代表性论文 | 是 |
七大方向——子方向分类 | 脑机接口 |
国重实验室规划方向分类 | 认知机理与类脑学习 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51623 |
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 HG(何晖光) |
作者单位 | 1.Institute of Automation,Chinese Academy of Sciences 2.Huawei Noah’s Ark Lab, Beijing, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Du CD,Du CY,He HG. Doubly Semi-Supervised Multimodal Adversarial Learning for Classification, Generation and Retrieval[C]//IEEE,2019. |
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 | ||
ICME2019_Doubly Semi(636KB) | 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