About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Jun-Ho Choi
- sl:arxiv_num : 1904.09078
- sl:arxiv_published : 2019-04-19T04:46:29Z
- sl:arxiv_summary : Classification using multimodal data arises in many machine learning
applications. It is crucial not only to model cross-modal relationship
effectively but also to ensure robustness against loss of part of data or
modalities. In this paper, we propose a novel deep learning-based multimodal
fusion architecture for classification tasks, which guarantees compatibility
with any kind of learning models, deals with cross-modal information carefully,
and prevents performance degradation due to partial absence of data. We employ
two datasets for multimodal classification tasks, build models based on our
architecture and other state-of-the-art models, and analyze their performance
on various situations. The results show that our architecture outperforms the
other multimodal fusion architectures when some parts of data are not
available.@en
- sl:arxiv_title : EmbraceNet: A robust deep learning architecture for multimodal classification@en
- sl:arxiv_updated : 2019-04-19T04:46:29Z
- sl:bookmarkOf : https://arxiv.org/abs/1904.09078
- sl:creationDate : 2020-10-14
- sl:creationTime : 2020-10-14T09:55:10Z