Home /
Research
Showing 787 - 792 / 904
EAdam Optimizer: How $ε$ Impact Adam
WeiYuan, Kai-XinGao....
Published date-11/04/2020
Many adaptive optimization methods have been proposed and used in deep learning, in which Adam is regarded as the default algorithm and widely used in many deep learning frameworks. Recently, …
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding
MikeRoberts, NathanPaczan....
Published date-11/04/2020
indoorsceneunderstanding, Multi-TaskLearning, SceneUnderstanding
For many fundamental scene understanding tasks, it is difficult or impossible to obtain per-pixel ground truth labels from real images. We address this challenge by introducing Hypersim, a photorealistic synthetic …
PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents
RyoFujii, MasatoMita, KaoriAbe....
Published date-11/04/2020
MachineTranslation
Neural Machine Translation (NMT) has shown drastic improvement in its quality when translating clean input, such as text from the news domain. However, existing studies suggest that NMT still struggles …
Registration Loss Learning for Deep Probabilistic Point Set Registration
FelixJäremoLawin, Per-ErikForssén....
Published date-11/04/2020
Probabilistic methods for point set registration have interesting theoretical properties, such as linear complexity in the number of used points, and they easily generalize to joint registration of multiple point …
Low cost enhanced security face recognition with stereo cameras
BielTuraVecino, MartíCobos, PhilippeSalembier....
Published date-11/04/2020
FaceRecognition
This article explores a face recognition alternative which seeks to contribute to resolve current security vulnerabilities in most recognition architectures. Current low cost facial authentication software in the market can …
MK-SQuIT: Synthesizing Questions using Iterative Template-filling
BenjaminA.Spiegel, VincentCheong, JamesE.Kaplan....
Published date-11/04/2020
MachineTranslation
The aim of this work is to create a framework for synthetically generating question/query pairs with as little human input as possible. These datasets can be used to train machine …