Home /
Research
Showing 817 - 822 / 897
RealHePoNet: a robust single-stage ConvNet for head pose estimation in the wild
RafaelBerral-Soler, FranciscoJ.Madrid-Cuevas, RafaelMuñoz-Salinas....
Published date-11/03/2020
HeadPoseEstimation, PoseEstimation
Human head pose estimation in images has applications in many fields such as human-computer interaction or video surveillance tasks. In this work, we address this problem, defined here as the …
A Two-Stage Approach to Device-Robust Acoustic Scene Classification
HuHu, Chao-HanHuckYang, XianjunXia....
Published date-11/03/2020
AcousticSceneClassification, DataAugmentation, SceneClassification
To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is …
A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks
EdenBelouadah, AdrianPopescu, IoannisKanellos....
Published date-11/03/2020
IncrementalLearning
The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic …
BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration
MajedElHelou, SabineSüsstrunk....
Published date-11/03/2020
Colorization, Denoising, ImageRestoration
Image restoration encompasses fundamental image processing tasks that have been addressed with different algorithms and deep learning methods. Classical restoration algorithms leverage a variety of priors, either implicitly or explicitly. …
Tabular Transformers for Modeling Multivariate Time Series
InkitPadhi, YairSchiff, IgorMelnyk....
Published date-11/03/2020
FraudDetection, SyntheticDataGeneration, TimeSeries
Tabular datasets are ubiquitous in data science applications. Given their importance, it seems natural to apply state-of-the-art deep learning algorithms in order to fully unlock their potential. Here we propose …
Subword Segmentation and a Single Bridge Language Affect Zero-Shot Neural Machine Translation
AnnetteRios, MathiasMüller, RicoSennrich....
Published date-11/03/2020
MachineTranslation
Zero-shot neural machine translation is an attractive goal because of the high cost of obtaining data and building translation systems for new translation directions. However, previous papers have reported mixed …