We present a novel and robust method for localizing and segmenting bilaterally symmetric patterns from real-world images. On the basis of symmetrically matched pairs of local featu...
Minsu Cho (Seoul National University), Kyoung Mu L...
We address an unsupervised object detection and segmentation problem that goes beyond the conventional assumptions of one-to-one object correspondences or model-test settings betwe...
Minsu Cho (Seoul National University), Young Min S...
Abstract— In this paper we present a highly scalable visionbased localization and mapping method using image collections. A topological world representation is created online dur...
Friedrich Fraundorfer, Christopher Engels, David N...
Peephole optimizers are typically constructed using human-written pattern matching rules, an approach that requires expertise and time, as well as being less than systematic at ex...
This paper explores how to characterise security properties of software components, and how to reason about their suitability for a trustworthy compositional contract. Our framewo...