[论文记录] 2021 - ArtEmis: Affective Language for Visual Art
论文简介
原论文:ArtEmis: Affective Language for Visual Art1
视觉艺术中的情感语言
论文地址:https://arxiv.org/abs/2101.07396
以下仅为作者阅读论文时的记录,学识浅薄,如有错误,欢迎指正。
论文内容
摘要
-
We present a novel large-scale dataset and accompanying machine learning models aimed at providing a detailed understanding of the interplay between visual content, its emotional effect, and explanations for the latter in language.
我们提出了一个新的大规模数据集以及相应的机器学习模型,为了详细理解有关视觉内容之间关联性及其情感效应,并用语言对后者进行解释。 -
In contrast to most existing annotation datasets in computer vision, we focus on the affective experience triggered by visual artworks and ask the annotators to indicate the dominant emotion they feel for a given image and, crucially, to also provide a grounded verbal explanation f