US Patent 11244162 Automatic identification of relationships between a center of attention and other individuals/objects present in an image or video

A computer-implemented method includes: accessing, by a computing device, content stored or captured by a user device; determining, by the computing device, context associated with the content; determining, by the computing device, a center of attention of the content based on the context; identifying, by the computing device, relationships between the center of attention and one or more other individuals or objects present in the content; and outputting, by the computing device, information identifying the relationships for displaying the information identifying the relationships on a content viewer application.