There are multiple and even interacting dimensions along which shape representation schemes may be compared and contrasted. In this paper, we focus on the following ques- tion. Are the building blocks in a compositional model lo- calized in space (e.g. as in part based representations) or are they holistic simplifications (e.g. as in spectral representa- tions)? Existing shape representation schemes prefer one or the other. We propose a new shape representation paradigm that encompasses both choices.
In this paper we show how the shape of a 2D-landmark configuration can be encoded based on qualitative 1D-ordering information and how relevant geometric shape properties of a landmark configuration (strictly based on ordering information) can be detected by a sequence of view-based snapshots. Furthermore we show how shape of landmark configurations supports view-based localization tasks specially in the face of erroneous and missing sensor information.
The titles of the seven symposia were Artificial Intelligence for Development; Cognitive Shape Processing; Educational Robotics and Beyond: Design and Evaluation; Embedded Reasoning: Intelligence in Embedded Systems; Intelligent Information Privacy Management; It's All in the Timing: Representing and Reasoning about Time in Interactive Behavior; and Linked Data Meets Artificial Intelligence. The Symposium on Artificial Intelligence for Development was organized to explore opportunities for using machine learning, inference, planning, and perception to enhance the quality of lives of disadvantaged populations. Over the last several years, a community of researchers with interest in applying computing and communication technologies in developing regions has come together under the label Information and Communication Technology for Development (ICT-D). However, ICT-D efforts to date have rarely focused on opportunities to harness machine learning, reasoning, and perception to create intelligent systems, services, models, and analyses. Beyond exploring research projects and directions, we hoped that bringing together a critical mass of researchers who share an interest in applying AI to development challenges would serve to help launch a new vibrant subfield of ICT-D on artificial intelligence for development (AID).
Barkowsky, Thomas (University of Bremen) | Bertel, Sven (University of Illinois at Urbana-Champaign) | Broz, Frank (University of Hertfordshire) | Chaudhri, Vinay K. (SRI International) | Eagle, Nathan (txteagle, Inc.) | Genesereth, Michael (Stanford University) | Halpin, Harry (University of Edinburgh) | Hamner, Emily (Carnegie Mellon University) | Hoffmann, Gabe (Palo Alto Research Center) | Hölscher, Christoph (University of Freiburg) | Horvitz, Eric (Microsoft Research) | Lauwers, Tom (Carnegie Mellon University) | McGuinness, Deborah L. (Rensselaer Polytechnic Institute) | Michalowski, Marek (BeatBots LLC) | Mower, Emily (University of Southern California) | Shipley, Thomas F. (Temple University) | Stubbs, Kristen (iRobot) | Vogl, Roland (Stanford University) | Williams, Mary-Anne (University of Technology)
The Association for the Advancement of Artificial Intelligence, in cooperation with Stanford University’s Department of Computer Science, is pleased to present the 2010 Spring Symposium Series, to be held Monday through Wednesday, March 22–24, 2010 at Stanford University. The titles of the seven symposia are Artificial Intelligence for Development; Cognitive Shape Processing; Educational Robotics and Beyond: Design and Evaluation; Embedded Reasoning: Intelligence in Embedded Systems Intelligent Information Privacy Management; It’s All in the Timing: Representing and Reasoning about Time in Interactive Behavior; and Linked Data Meets Artificial Intelligence.
Convolutional Neural Networks (CNN) have been successful in processing data signals that are uniformly sampled in the spatial domain (e.g., images). However, most data signals do not natively exist on a grid, and in the process of being sampled onto a uniform physical grid suffer significant aliasing error and information loss. Moreover, signals can exist in different topological structures as, for example, points, lines, surfaces and volumes. It has been challenging to analyze signals with mixed topologies (for example, point cloud with surface mesh). To this end, we develop mathematical formulations for Non-Uniform Fourier Transforms (NUFT) to directly, and optimally, sample nonuniform data signals of different topologies defined on a simplex mesh into the spectral domain with no spatial sampling error. The spectral transform is performed in the Euclidean space, which removes the translation ambiguity from works on the graph spectrum. Our representation has four distinct advantages: (1) the process causes no spatial sampling error during the initial sampling, (2) the generality of this approach provides a unified framework for using CNNs to analyze signals of mixed topologies, (3) it allows us to leverage state-of-the-art backbone CNN architectures for effective learning without having to design a particular architecture for a particular data structure in an ad-hoc fashion, and (4) the representation allows weighted meshes where each element has a different weight (i.e., texture) indicating local properties. We achieve results on par with the state-of-the-art for the 3D shape retrieval task, and a new state-of-the-art for the point cloud to surface reconstruction task.