Abstract. We describe an efficient approach to construct shape models composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts ...
Knowing the subcellular location of a protein is critical to a full understanding of its function, and automated, objective methods for assigning locations are needed as part of t...
This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
: One of the main operations in conceptual 3D design is the rearrangement of single and composite objects. This paper presents a new conceptual 3D design system that affords easy m...
Abstract. Context plays an important role in general scene perception. In particular, it can provide cues about an object’s location within an image. In computer vision, object d...