Home /
Research
Showing 415 - 420 / 897
DiffusionNet: Accelerating the solution of Time-Dependent partial differential equations using deep learning
MahmoudAsem....
Published date-11/19/2020
We present our deep learning framework to solve and accelerate the Time-Dependent partial differential equation's solution of one and two spatial dimensions. We demonstrate DiffusionNet solver by solving the 2D …
Exploring Text Specific and Blackbox Fairness Algorithms in Multimodal Clinical NLP
JohnChen, IanBerlot-Atwell, SafwanHossain....
Published date-11/19/2020
fairness, WordEmbeddings
Clinical machine learning is increasingly multimodal, collected in both structured tabular formats and unstructured forms such as freetext. We propose a novel task of exploring fairness on a multimodal clinical …
Creative Sketch Generation
SongweiGe, VedanujGoswami, C.LawrenceZitnick....
Published date-11/19/2020
Sketching or doodling is a popular creative activity that people engage in. However, most existing work in automatic sketch understanding or generation has focused on sketches that are quite mundane. …
Dense Label Encoding for Boundary Discontinuity Free Rotation Detection
XueYang, LipingHou, YueZhou....
Published date-11/19/2020
SceneText
Rotation detection serves as a fundamental building block in many visual applications involving aerial image, scene text, and face etc. Differing from the dominant regression-based approaches for orientation estimation, this …
Unmixing Convolutional Features for Crisp Edge Detection
LinxiHuan, XianweiZheng, NanXue....
Published date-11/19/2020
EdgeDetection
This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly …
Improving Bayesian Network Structure Learning in the Presence of Measurement Error
YangLiu, AnthonyC.Constantinou, ZhigaoGuo....
Published date-11/19/2020
Structure learning algorithms that learn the graph of a Bayesian network from observational data often do so by assuming the data correctly reflect the true distribution of the variables. However, …