261 citations
- ETH ZurichCH12 papers
- Walt Disney (United States)US5 papers
- Adobe Systems (United States)US2 papers
- Beihang UniversityCN2 papers
- University of Southern CaliforniaUS2 papers
- University of WaterlooCA2 papers
- University of Wisconsin–MadisonUS2 papers
- Aristotle University of ThessalonikiGR1 paper
- Coventry UniversityGB1 paper
- École de Technologie SupérieureCA1 paper
- Fraunhofer Institute for Computer Graphics ResearchDE1 paper
- German Research Centre for Artificial IntelligenceDE1 paper
5 papers · 1 filter
Unsupervised Deep Representations for Learning Audience Facial Behaviors
Suman Saha, Rajitha Navarathna, Leonhard Helminger +1
In this paper, we present an unsupervised learning approach for analyzing facial behavior based on a deep generative model combined with a convolutional neural network (CNN). We jo…
On Regularized Losses for Weakly-supervised CNN Segmentation
Meng Tang, Federico Perazzi, Abdelaziz Djelouah +3
Minimization of regularized losses is a principled approach to weak supervision well-established in deep learning, in general. However, it is largely overlooked in semantic segment…
Normalized Cut Loss for Weakly-supervised CNN Segmentation
Meng Tang, Abdelaziz Djelouah, Federico Perazzi +2
Most recent semantic segmentation methods train deep convolutional neural networks with fully annotated masks requiring pixel-accuracy for good quality training. Common weakly-supe…
Active Mini-Batch Sampling using Repulsive Point Processes
Cheng Zhang, Cengiz Öztireli, Stephan Mandt +1
The convergence speed of stochastic gradient descent (SGD) can be improved by actively selecting mini-batches. We explore sampling schemes where similar data points are less likely…
Single Day Outdoor Photometric Stereo
Yannick Hold-Geoffroy, Paulo F. U. Gotardo, Jean-François Lalonde
Photometric Stereo (PS) under outdoor illumination remains a challenging, ill-posed problem due to insufficient variability in illumination. Months-long capture sessions are typica…