by Martina Haefeli | Jul 23, 2017 | Video Processing, Visual Computing
Painting by Feature In this paper, we propose a reinterpretation of the brush and the fill tools for digital image painting. July 21, 2013ACM SIGGRAPH 2013 Authors Michal Lukac (CTU in Prague, FEE) Jakub Fiser (CTU in Prague, FEE) Jean-Charles Bazin (ETH...
by Martina Haefeli | Jul 22, 2017 | Machine Learning, Story Technology, Visual Computing
Factorized Variational Autoencoders for Modeling Audience Reactions to Movies In this paper, we study non-linear tensor factorization methods based on deep variational autoencoders. July 22, 2017IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017...
by Martina Haefeli | Jul 22, 2017 | Machine Learning, Video Processing, Visual Computing
One-Shot Metric Learning for Person Re-identification The proposed one-shot learning achieves performance that is competitive with supervised methods but uses only a single example rather than the hundreds required for the fully supervised case. July 22, 2017IEEE...
by Martina Haefeli | Jul 22, 2017 | Capture, Visual Computing
A Practical Method for Fully Automatic Intrinsic Camera Calibration Using Directionally Encoded Light We propose a novel calibration method based on the usage of directionally encoded light rays for estimating the intrinsic parameters. July 22, 2017IEEE Conference...
by Martina Haefeli | Jul 21, 2017 | AR/VR, Artificial Intelligence, Machine Learning, Story Technology, Visual Computing
Weakly-supervised Visual Grounding of Phrases with Linguistic Structures We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention...