Our objective was to determine the most energy efficient 64b static CMOS adder architecture, for a range of high-performance delay targets. We examine extensively carry-lookahead ...
We present a novel image classification technique for detecting multiple objects (called subobjects) in a single image. In addition to image classifiers, we apply spatial relati...
Remarkable performance has been reported to recognize single object classes. Scalability to large numbers of classes however remains an important challenge for today's recogn...
Marcus Rohrbach, Michael Stark, Gyö Szarvas, Bern...
Many successful models for scene or object recognition transform low-level descriptors (such as Gabor filter responses, or SIFT descriptors) into richer representations of interme...
Y-Lan Boureau, Francis Bach, Yann LeCun, Jean Ponc...
Surface registration is a fundamental step in the reconstruction of three-dimensional objects. This is typically a two step process where an initial coarse motion estimation is fo...