“Hierarchical Multi-Label Attribute Classification With Graph Convolutional Networks on Anime Illustration”, 2023-04-10 (; backlinks):
In this study, we present a hierarchical multi-modal multi-label attribute classification model for anime illustrations using graph convolutional networks (GCNs). The focus of this study is multi-label attribute classification, as creators of anime illustrations frequently and deliberately emphasize subtle features of characters and objects.
To analyze the connections between attributes, we develop a multi-modal GCN-based model that can use semantic features of anime illustrations. To create features representing the semantic information of anime illustrations, we construct a novel captioning framework by combining real-world images with their animated style transformations.
In addition, because the attributes of anime illustrations are hierarchical, we introduce a loss function that considers the hierarchy of attributes to improve classification accuracy.
The proposed method has two main contributions: (1) By introducing a GCN with semantic features into the multi-label attribute classification task of anime illustrations, we capture more comprehensive relationships between attributes. (2) By following certain rules to build a hierarchical structure of attributes that appear frequently in anime illustrations, we further capture subordinate relationships between attributes.
In addition, we demonstrate the effectiveness of the proposed method by experiments.
See Also: