Predicting Video Affect via Induced Affection in the Wild
Predicting Video Affect via Induced Affection in the Wild
复制标题
DOI：
10.1145/3382507.3418838
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Yi Ding;Radha Kumaran;Tianjiao Yang;Tobias Höllerer
中科院分区：
文献类型：
--
作者：
Yi Ding;Radha Kumaran;Tianjiao Yang;Tobias Höllerer
管理用于研究影响的大型高质量数据集是一个昂贵且耗时的过程，特别是当标签是连续的时。在本文中，我们研究了使用文本评论的形式，以帮助分类视频影响未标记的公众反应的潜力。我们研究了两个流行的数据集，用于影响识别和挖掘公众对这些视频的反应。我们通过使用视频评级作为弱监督信号来学习这些反应的表示。我们证明了，当只给一个视频时，我们的模型可以学习评论影响的细粒度预测。此外，我们还演示了预测评论的情感属性如何成为多模态情感建模中潜在有用的模态。
Curating large and high quality datasets for studying affect is a costly and time consuming process, especially when the labels are continuous. In this paper, we examine the potential to use unlabeled public reactions in the form of textual comments to aid in classifying video affect. We examine two popular datasets used for affect recognition and mine public reactions for these videos. We learn a representation of these reactions by using the video ratings as a weakly supervised signal. We show that our model can learn a fine-graind prediction of comment affect when given a video alone. Furthermore, we demonstrate how predicting the affective properties of a comment can be a potentially useful modality to use in multimodal affect modeling.