Abstract— Linking semantic and spatial information has become an important research area in robotics since, for robots interacting with humans and performing tasks in natural env...
Object detection and pixel-wise scene labeling have both been active research areas in recent years and impressive results have been reported for both tasks separately. The integra...
Humans can easily recognize complex objects even if values of their attributes are imprecise and often inconsistent. It is not clear how the brain processes uncertain visual inform...
Psychologists have proposed that many human-object interaction activities form unique classes of scenes. Recognizing these scenes is important for many social functions. To enable...
To find out how the representations of structured visual objects depend on the co-occurrence statistics of their constituents, we exposed subjects to a set of composite images wit...
Shimon Edelman, Benjamin P. Hiles, Hwajin Yang, Na...