by Sarah Frigg | Jul 11, 2016 | Animation, Visual Computing
Real-time Skeletal Skinning with Optimized Centers of Rotation Our method significantly reduces the artifacts of LBS and DQS while maintaining real-time performance and backwards compatibility with the animation pipeline. July 11, 2016ACM SIGGRAPH 2016 ...
by Sarah Frigg | Jul 10, 2016 | Digital Fabrication
A Compiler for 3D Machine Knitting We present a compiler that can automatically turn assemblies of high-level shape primitives (tubes, sheets) into low-level machine instructions. July 10, 2016ACM SIGGRAPH 2016 Authors James McCann (Disney Research) Lea...
by Sarah Frigg | Jun 24, 2016 | Machine Learning, Visual Computing
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. June 24, 2016IEEE Conference on Computer...
by Sarah Frigg | Jun 24, 2016 | Visual Computing
Harnessing Object and Scene Semantics for Large-Scale Video Understanding We propose a novel object- and scene-based semantic fusion network and representation. June 24, 2016Accepted at IEEE Conference on Computer Vision Pattern Recognition (CVPR) 2016 ...
by Sarah Frigg | Jun 24, 2016 | Machine Learning, Visual Computing
Completed Semi-supervised Vocabulary-informed Learning We propose the notion of semi-supervised vocabulary-informed learning to alleviate the above mentions challenges and address problems of supervised, zero-shot and open set recognition using a unified framework....
