Convolutional neural networks (CNNs) have massively impacted visual recognition in 2D images, and are now ubiquitous in state-of-the-art approaches. CNNs do not easily extend, however, to data that are not represented by regular grids, such as 3D shape meshes or other graphstructured data, to which traditional local convolution operators do not directly apply. To address this problem, we propose a novel graph-convolution operator to establish correspondences between filter weights and graph neighborhoods with arbitrary connectivity. The key novelty of our approach is that these correspondences are dynamically computed from features learned by the network, rather than relying on predefined static coordinates over the graph as in previous work. We obtain excellent experimental results that significantly improve over previous state-of-theart shape correspondence results. This shows that our approach can learn effective shape representations from raw input coordinates, without relying on shape descriptors.
Faced with the increasing need for correctly designed hybrid and cyber-physical systems today, the problem of including provision for continuously varying behaviour as well as the usual discrete changes of state is considered in the context of Event-B. An extension of Event-B called Hybrid Event-B is presented, that accommodates continuous behaviours (called pliant events) in between familiar discrete transitions (called mode events in this context). The continuous state change can be specified by a combination of indirect specification via ordinary differential equations, or direct specification via assignment of variables to values that depend on time, or indirect specification by demanding that behaviour obeys a time dependent predicate. The syntactic elements of the extension are discussed, and the semantics is described in terms of the properties of time dependent valuations of variables. Refinement is examined in detail, with reference to the notion of refinement inherited from discrete Event-B. A full suite of proof obligations is presented, covering all aspects of the new framework. A selection of examples and case studies is presented. A particular challenge -bearing in mind the desirability of conforming to existing intuitions about discrete Event-B, and the impact on tool support (as embodied in tools for discrete Event-B like Rodin)-is to design the whole framework so as to disturb as little as possible the existing structures for handling discrete Event-B.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations鈥揷itations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.