Invariant representations in object recognition systems are generally obtained by pooling feature vectors over spatially local neighborhoods. But pooling is not local in the featu...
Y-Lan Boureau, Nicolas Le Roux, francis bach, Jean...
We introduce layer operations for single-view 3D deformable object manipulation, in which the user can control the depth order of layered 3D objects resting on a flat ground with...
Abstract. The complexity of visual representations is substantially limited by the compositional nature of our visual world which, therefore, renders learning structured object mod...
— Object recognition is a challenging problem for artificial systems. This is especially true for objects that are placed in cluttered and uncontrolled environments. To challenge...
—We present a novel algorithm to segment a 3D surface mesh into visually meaningful regions. Our approach is based on an analysis of the local geometry of vertices. In particular...