T
Tomas Pfister
Researcher at Google
Publications - 109
Citations - 8894
Tomas Pfister is an academic researcher from Google. The author has contributed to research in topics: Computer science & Pose. The author has an hindex of 26, co-authored 81 publications receiving 5436 citations. Previous affiliations of Tomas Pfister include University of Oulu & University of Technology, Sydney.
Papers
More filters
Proceedings ArticleDOI
Learning from Simulated and Unsupervised Images through Adversarial Training
TL;DR: SimGAN as mentioned in this paper uses an adversarial network similar to Generative Adversarial Networks (GANs), but with synthetic images as inputs instead of random vectors, and achieves state-of-the-art results on the MPIIGaze dataset without any labeled real data.
Posted Content
Learning from Simulated and Unsupervised Images through Adversarial Training
TL;DR: This work develops a method for S+U learning that uses an adversarial network similar to Generative Adversarial Networks (GANs), but with synthetic images as inputs instead of random vectors, and makes several key modifications to the standard GAN algorithm to preserve annotations, avoid artifacts, and stabilize training.
Proceedings ArticleDOI
Flowing ConvNets for Human Pose Estimation in Videos
TL;DR: This work proposes a ConvNet architecture that is able to benefit from temporal context by combining information across the multiple frames using optical flow and outperforms a number of others, including one that uses optical flow solely at the input layers, one that regresses joint coordinates directly, and one that predicts heatmaps without spatial fusion.
Proceedings ArticleDOI
A Spontaneous Micro-expression Database: Inducement, collection and baseline
TL;DR: A novel Spontaneous Micro-expression Database SMIC is presented, which includes 164 micro-expression video clips elicited from 16 participants and provides sufficient source material for comprehensive testing of automatic systems for analyzing micro-expressions, which has not been possible with any previously published database.
Posted Content
TabNet: Attentive Interpretable Tabular Learning
Sercan O. Arik,Tomas Pfister +1 more
TL;DR: It is demonstrated that TabNet outperforms other neural network and decision tree variants on a wide range of non-performance-saturated tabular datasets and yields interpretable feature attributions plus insights into the global model behavior.