论文标题
无监督的漫画角色通过面部和时空相关聚类重新识别
Unsupervised Manga Character Re-identification via Face-body and Spatial-temporal Associated Clustering
论文作者
论文摘要
在过去的几年中，E-Manga（电子日本风格的漫画）急剧增长。面对漫画研究的繁荣需求和大量未标记的漫画数据，我们提出了一项新任务，称为无监督的漫画重新识别。但是，漫画的艺术表达和风格局限性在重新识别问题上构成了许多挑战。灵感来自某些与内容相关的特征可能有助于聚类的想法，我们提出了一种面部和时空相关的聚类方法（FSAC）。在面部组合模块中，通过使用图像的完整性来构建面部图形以解决艺术创造中夸张和变形等问题。在时空关系校正模块中，我们分析了字符的外观特征，并设计了与时间空间相关的三胞胎损失，以微调聚类。具有109卷的漫画书数据集上的广泛实验验证了我们方法在无监督的漫画重新识别中的优越性。
In the past few years, there has been a dramatic growth in e-manga (electronic Japanese-style comics). Faced with the booming demand for manga research and the large amount of unlabeled manga data, we raised a new task, called unsupervised manga character re-identification. However, the artistic expression and stylistic limitations of manga pose many challenges to the re-identification problem. Inspired by the idea that some content-related features may help clustering, we propose a Face-body and Spatial-temporal Associated Clustering method (FSAC). In the face-body combination module, a face-body graph is constructed to solve problems such as exaggeration and deformation in artistic creation by using the integrity of the image. In the spatial-temporal relationship correction module, we analyze the appearance features of characters and design a temporal-spatial-related triplet loss to fine-tune the clustering. Extensive experiments on a manga book dataset with 109 volumes validate the superiority of our method in unsupervised manga character re-identification.
