by Martina Haefeli | Jun 27, 2016 | Machine Learning
Harnessing Object and Scene Semantics for Large-Scale Video Understanding We propose a novel object- and scene-based semantic fusion network and representation. June 27, 2016IEEE Conference on Computer Vision Pattern Recognition (CVPR) 2016 Authors...
by Martina Haefeli | Jun 27, 2016 | Machine Learning
Learning Activity Progression in LSTMs for Activity Detection and Early Detection In this work we improve training of temporal deep models to better learn activity progression for activity detection and early detection tasks. June 27, 2016IEEE Conference on Computer...
by Martina Haefeli | Jun 22, 2016 | Rendering, Visual Computing
Nonlinearly Weighted First-order Regression for Denoising Monte Carlo Renderings We address the problem of denoising Monte Carlo renderings by studying existing approaches and proposing a new algorithm that yields state-of-the-art performance on a wide range of...
by Martina Haefeli | Jun 20, 2016 | Digital Fabrication, Visual Computing
Stenciling: Designing Structurally-Sound Surfaces with Decorative Patterns We present a novel method to design shells with artistic cutouts in a manner that produces a stable final result. June 20, 2016Eurographics Symposium on Geometry Processing 2016 ...
by Martina Haefeli | May 7, 2016 | Digital Fabrication, Visual Computing
DefSense: Computational Design of Customized Deformable Input Devices We present a novel optimization-based algorithm for the design and fabrication of customized, deformable input devices, capable of continuously sensing their deformation. May 7, 2016CHI...
