We propose a new approach -- called PK-clustering to help social scientists create meaningful clusters in networks. Many clustering algorithms exist but most find them difficult understand, and tools do not provide any guidance choose algorithms, or evaluate results taking into account the prior knowledge of scientists. Our work introduces visual analytics user interface that address this issue...

A major challenge in scene graph classification is that the appearance of objects and relations can be significantly different from one image to another. Previous works have addressed this by relational reasoning over all an or incorporating prior knowledge into classification. Unlike previous works, we do not consider separate models for perception knowledge. Instead, take a multi-task learnin...