图 书 馆
艺术影响的知识发现：一种度量学习方法Knowledge Discovery of Artistic Influences: A Metric Learning Approach |
|
| 课程网址: | http://videolectures.net/iccc2014_elgammal_metric_learning/ |
| 主讲教师: | Ahmed Elgammal |
| 开课单位: | 新泽西州立大学 |
| 开课时间: | 2014-08-08 |
| 课程语种: | 英语 |
| 中文简介: |  我们解决了一个挑战性的问题，即根据画家的美术作品发现画家之间的影响。在这项工作中，我们专注于在视觉相似性方面比较两名画家的绘画。这种比较是全自动的，并且基于计算机视觉方法和机器学习。我们基于两种不同的量度学习算法，研究了不同的视觉特征和相似性度量，以找到最适合艺术主题的算法。我们通过将其结果与地面真相注释进行比较来评估我们的方法，从而收集了大量美术作品。 |
| 课程简介: | We approach the challenging problem of discovering influences between painters based on their fine-art paintings. In this work, we focus on comparing paintings of two painters in terms of visual similarity. This comparison is fully automatic and based on computer vision approaches and machine learning. We investigated different visual features and similarity measurements based on two different metric learning algorithms to find the most appropriate ones that follow artistic motifs. We evaluated our approach by comparing its result with ground truth annotation for a large collection of fine-art paintings. |
| 关 键 词: | 学习算法; 相似性度量 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-05-08：zyk |
| 最后编审: | 2021-05-08：zyk |
| 阅读次数: | 40 |