Cashman T.J.,University of Lugano |
IEEE Transactions on Pattern Analysis and Machine Intelligence | Year: 2013
3D morphable models are low-dimensional parameterizations of 3D object classes which provide a powerful means of associating 3D geometry to 2D images. However, morphable models are currently generated from 3D scans, so for general object classes such as animals they are economically and practically infeasible. We show that, given a small amount of user interaction (little more than that required to build a conventional morphable model), there is enough information in a collection of 2D pictures of certain object classes to generate a full 3D morphable model, even in the absence of surface texture. The key restriction is that the object class should not be strongly articulated, and that a very rough rigid model should be provided as an initial estimate of the “mean shape.” The model representation is a linear combination of subdivision surfaces, which we fit to image silhouettes and any identifiable key points using a novel combined continuous-discrete optimization strategy. Results are demonstrated on several natural object classes, and show that models of rather high quality can be obtained from this limited information. © 1979-2012 IEEE.
Schmidhuber J.,University of Lugano
Neural Networks | Year: 2015
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks. © 2014.
Bronstein M.M.,University of Lugano |
Bronstein A.M.,Tel Aviv University
IEEE Transactions on Pattern Analysis and Machine Intelligence | Year: 2011
Recent works have shown the use of diffusion geometry for various pattern recognition applications, including nonrigid shape analysis. In this paper, we introduce spectral shape distance as a general framework for distribution-based shape similarity and show that two recent methods for shape similarity due to Rustamov and Mahmoudi and Sapiro are particular cases thereof. © 2006 IEEE.
Hannawa A.F.,University of Lugano
Patient Education and Counseling | Year: 2014
Objective: The purpose of this study was to test causal effects of physicians' nonverbal involvement on medical error disclosure outcomes. Methods: 216 hospital outpatients were randomly assigned to two experimental treatment groups. The first group watched a video vignette of a verbally effective and nonverbally involved error disclosure. The second group was exposed to a verbally effective but nonverbally uninvolved error disclosure. All patients responded to seven outcome measures. Results: Patients in the nonverbally uninvolved error disclosure treatment group perceived the physician's apology as less sincere and remorseful compared to patients in the involved disclosure group. They also rated the implications of the error as more severe, were more likely to ascribe fault to the physician, and indicated a higher intent to change doctors after the disclosure. Conclusion: The results of this study imply that nonverbal involvement during medical error disclosures facilitates more accurate patient understanding and assessment of the medical error and its consequences on their health and quality of life. Practice implications: In the context of disclosing medical errors, nonverbal involvement increases the likelihood that physicians will be able to continue caring for their patient. Thus, providers are advised to consider adopting this communication skill into their medical practice. © 2013 Elsevier Ireland Ltd.
Cashman T.J.,University of Lugano
Computer Graphics Forum | Year: 2012
Subdivision surfaces allow smooth free-form surface modelling without topological constraints. They have become a fundamental representation for smooth geometry, particularly in the animation and entertainment industries. This survey summarizes research on subdivision surfaces over the last 15 years in three major strands: analysis, integration into existing systems and the development of new schemes. We also examine the reason for the low adoption of new schemes with theoretical advantages, explain why Catmull-Clark surfaces have become a de facto standard in geometric modelling, and conclude by identifying directions for future research. © 2012 The Author.