情感计算的三种输入类型——
a) behavioral responses to emotional stimuli expressed through an interactive application
b) objective data collected as bodily responses to stimuli, such as physiological signals and facial expressions
c) the context of the interaction
情感计算的模型建立——
在之前要提取特征 DL、PCA、Fisher projection 尤其是DL方法可以消除特征提取的一些局限性
情感计算的输出表达——
preference-based (or ranking-based) annotations for emotion (e.g., X is more frustrating than Y)
rating-based annotation (such as the self-assessment manikins, a tool to rate levels of arousal and valence in discrete or continuous scales)
本文使用前者
preference deep learning——PDL: the use of deep ANN architectures trained on ranked (pairwise preference) annotations of affect
网络结构是传统的CNN和自编码器
在损失函数上有所创新： Rank Margin error function
The function becomes zero if this difference is greater than 1, i.e., there is enough margin to separate the preferred “positive example” score f(xP) from the nonpreferred “negative example” score f (xN)
最后比较了ad-hoc feature和PDL feature
Results, in general, suggest that DL methodologies are highly appropriate for affective modeling and, more importantly, indicate that ad-hoc feature extraction can be redundant for physiology-based modeling.
时间久远 工作现在看起来比较简单
注意如果看不下去某篇文章 有可能是你想要看的内容已经都看到了 所以失去了兴趣
在每篇文章中都有收获 不一定要逐字逐句读完。
Martinez H P, Bengio Y, Yannakakis G N. Learning deep physiological models of affect[J]. IEEE Computational Intelligence Magazine, 2013, 8(2):20-33.