OmniArt
OmniArt
复制标题
奥尼艺术
DOI：
10.1145/3273022
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
M. Worring
中科院分区：
文献类型：
--
作者：
Gjorgji Strezoski;M. Worring
基线是任何定量多媒体研究的起点，而基准是推动这些基线进一步发展的关键。在这篇文章中，我们用一个名为OmniArt的新基准数据集呈现艺术领域的基线，该数据集包含超过200万张图像和丰富的结构化元数据。OmniArt包含对数十种属性类型的注释，并通过概念、图标类标签、颜色信息和(有限的)对象级边界框提供语义上下文信息。对于我们的数据集，我们建立并展示了多个任务的基线分数，例如艺术家归因、创作时期估计、类型、风格和学校预测。除了元数据相关的实验之外，我们还通过不同的类型探索了艺术的色彩空间，并评估了一个迁移学习对象识别管道。
Baselines are the starting point of any quantitative multimedia research, and benchmarks are essential for pushing those baselines further. In this article, we present baselines for the artistic domain with a new benchmark dataset featuring over 2 million images with rich structured metadata dubbed OmniArt. OmniArt contains annotations for dozens of attribute types and features semantic context information through concepts, IconClass labels, color information, and (limited) object-level bounding boxes. For our dataset we establish and present baseline scores on multiple tasks such as artist attribution, creation period estimation, type, style, and school prediction. In addition to our metadata related experiments, we explore the color spaces of art through different types and evaluate a transfer learning object recognition pipeline.