The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
This contribution proposes a compositionality architecture for visual object categorization, i.e., learning and recognizing multiple visual object classes in unsegmented, cluttered...
Imitation in artificial systems involves a number of important aspects, such as extracting the relevant features of the demonstrated behaviour, inverse mapping observations, and e...
We seek to both detect and segment objects in images. To exploit both local image data as well as contextual information, we introduce Boosted Random Fields (BRFs), which use boos...
Antonio Torralba, Kevin P. Murphy, William T. Free...
We propose Recursive Compositional Models (RCMs) for simultaneous multi-view multi-object detection and parsing (e.g. view estimation and determining the positions of the object s...
Leo Zhu, Yuanhao Chen, Antonio Torralba, William F...