Leonidas J. Guibas

TL;DR: In this paper, it was shown that for any collection of n hyperplanes in 3-space, the combinatorial complexity of the decomposition of the arrangementA(?) of? is O(n4 logn).

TL;DR: PeerNets is introduced, a novel family of convolutional networks alternating classical Euclidean convolutions with graph convolutions to harness information from a graph of peer samples that is up to 3 times more robust to a variety of white- and black-box adversarial attacks compared to conventional architectures with almost no drop in accuracy.

TL;DR: The identity management problem is the problem of probabilistically keeping track of the association between target tracks and target identities, based on observations made by sensors as discussed by the authors, which is the most common problem in identity management.

Abstract: We introduce a novel neural network architecture for encoding and synthesis of 3D shapes, particularly their structures. Our key insight is that 3D shapes are effectively characterized by their hierarchical organization of parts, which reflects fundamental intra-shape relationships such as adjacency and symmetry. We develop a recursive neural net (RvNN) based autoencoder to map a flat, unlabeled, arbitrary part layout to a compact code. The code effectively captures hierarchical structures of man-made 3D objects of varying structural complexities despite being fixed-dimensional: an associated decoder maps a code back to a full hierarchy. The learned bidirectional mapping is further tuned using an adversarial setup to yield a generative model of plausible structures, from which novel structures can be sampled. Finally, our structure synthesis framework is augmented by a second trained module that produces fine-grained part geometry, conditioned on global and local structural context, leading to a full generative pipeline for 3D shapes. We demonstrate that without supervision, our network learns meaningful structural hierarchies adhering to perceptual grouping principles, produces compact codes which enable applications such as shape classification and partial matching, and supports shape synthesis and interpolation with significant variations in topology and geometry.

TL;DR: The problem of distributing time-sensitive information from a collection of sources to mobile users traversing a wireless mesh network is considered and a set of well-placed nodes (warehouses) are selected to act as intermediaries between the information sources and clusters of users.