Apple Inc.

About: Apple Inc. is a company organization based out in Herzliya, Israel. It is known for research contribution in the topics: Signal & User interface. The organization has 15687 authors who have published 22600 publications receiving 624507 citations. The organization is also known as: Apple Computer, Inc. & Apple Computer Inc.

A Distributed Algorithm for Minimum-Weight Spanning Trees

Abstract: Abstract : A distributed algorithm is presented that constructs the minimum weight spanning tree in a connected undirected graph with distinct edge weights. A processor exists at each node of the graph, knowing initially only the weights of the adjacent edges. The processors obey the same algorithm and exchange messages with neighbors until the tree is constructed. The total number of messages required for a graph of N nodes and E edges is at most 5N log of N to the base 2 + 2E and a message contains at most one edge weight plus log of 8N to the base 2 bits. The algorithm can be initiated spontaneously at any node or at any subset of nodes.

Watch what I do: programming by demonstration

Abstract: Part 1 Systems: Pygmalion tinker a predictive calculator rehearsal world smallStar peridot metamouse TELS eager garnet the Turvy experience chimera the geometer's sketchpad tourmaline a history-based macro by example system mondrian triggers the AIDE project. Part 2 Components: a history of editable graphical histories graphical representation and feedback in a PBD system PBD invocation techniques a system-wide macro facility based on aggregate events making programming accessible to visual problem solvers using voice input to disambiguate intent. Part 3 Perspectives: characterizing PBD systems demonstrational interfaces just-in-time programming.

Touch screen liquid crystal display

Abstract: Disclosed herein are liquid-crystal display (LCD) touch screens that integrate the touch sensing elements with the display circuitry. The integration may take a variety of forms. Touch sensing elements can be completely implemented within the LCD stackup but outside the not between the color filter plate and the array plate. Alternatively, some touch sensing elements can be between the color filter and array plates with other touch sensing elements not between the plates. In another alternative, all touch sensing elements can be between the color filter and array plates. The latter alternative can include both conventional and in-plane-switching (IPS) LCDs. In some forms, one or more display structures can also have a touch sensing function. Techniques for manufacturing and operating such displays, as well as various devices embodying such displays are also disclosed.

Learning from Simulated and Unsupervised Images through Adversarial Training

Abstract: With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations. However, learning from synthetic images may not achieve the desired performance due to a gap between synthetic and real image distributions. To reduce this gap, we propose Simulated+Unsupervised (S+U) learning, where the task is to learn a model to improve the realism of a simulator's output using unlabeled real data, while preserving the annotation information from the simulator. We develop a method for S+U learning that uses an adversarial network similar to Generative Adversarial Networks (GANs), but with synthetic images as inputs instead of random vectors. We make several key modifications to the standard GAN algorithm to preserve annotations, avoid artifacts, and stabilize training: (i) a 'self-regularization' term, (ii) a local adversarial loss, and (iii) updating the discriminator using a history of refined images. We show that this enables generation of highly realistic images, which we demonstrate both qualitatively and with a user study. We quantitatively evaluate the generated images by training models for gaze estimation and hand pose estimation. We show a significant improvement over using synthetic images, and achieve state-of-the-art results on the MPIIGaze dataset without any labeled real data.

Gesturing with a multipoint sensing device

Abstract: Methods and systems for implementing gestures with sensing devices are disclosed. More particularly, methods and systems related to gesturing with multipoint sensing devices are disclosed.