Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
Abstract. The complexity of visual representations is substantially limited by the compositional nature of our visual world which, therefore, renders learning structured object mod...
Abstract— This paper proposes a method for learning viewpoint detection models for object categories that facilitate sequential object category recognition and viewpoint planning...
Objects in scenes interact with each other in complex ways. A key observation is that these interactions manifest themselves as predictable visual patterns in the image. Discoveri...
We present a 3-D shape-based object recognition system for simultaneous recognition of multiple objects in scenes containing clutter and occlusion. Recognition is based on matchin...