.png){kind=icon}
返回
Multi-label, multi-task CNN approach for context-based emotion recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.inffus.2020.11.007.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper proposes a new deep learning architecture for context-based multi-label multi-task emotion recognition. The architecture is built from three main modules: (1) a body features extraction module, which is a pre-trained Xception network, (2) a scene features extraction module, based on a modified VGG16 network, and (3) a fusion-decision module. Moreover, three categorical and three continuous loss functions are compared in order to point out the importance of the synergy between loss functions when it comes to multi-task learning. Then, we propose a new loss function, the multi-label focal loss (MFL), based on the focal loss to deal with imbalanced data. Experimental results on EMOTIC dataset show that MFL with the Huber loss gave better results than any other combination and outperformed the current state of art on the less frequent labels.
Keyword:
Emotion recognition
Loss function
Multi-task machine learning
Deep learning
Unbalanced data
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
15.5
论文数:
4.2K
被引数:
2.7W
机构
引用论文
分享收藏Matrixlysis, an improved sample preparation method for recovery of Mycobacteria from animal tissue material.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏
查看更多内容