no code implementations • 29 Oct 2021 • Jaya Krishna Mandivarapu, Eric Bunch, Glenn Fung
In this work, we address the problem of few-shot document image classification under domain shift.
no code implementations • 25 Jun 2021 • Jaya Krishna Mandivarapu, Eric Bunch, Qian You, Glenn Fung
Recent advancements in large pre-trained computer vision and language models and graph neural networks has lent document image classification many tools.
Ranked #1 on Document Image Classification on Tobacco-3482 (Memory metric)
no code implementations • NeurIPS Workshop TDA_and_Beyond 2020 • Eric Bunch, Jeffery Kline, Daniel Dickinson, Suhaas Bhat, Glenn Fung
Metric space magnitude, an active field of research in algebraic topology, is a scalar quantity that summarizes the effective number of distinct points that live in a general metric space.
no code implementations • 15 Feb 2021 • Bryan Bischof, Eric Bunch
We experimentally investigate a collection of feature engineering pipelines for use with a CNN for classifying eyes-open or eyes-closed from electroencephalogram (EEG) time-series from the Bonn dataset.
no code implementations • NeurIPS Workshop TDA_and_Beyond 2020 • Eric Bunch, Qian You, Glenn Fung, Vikas Singh
Recently, neural network architectures have been developed to accommodate when the data has the structure of a graph or, more generally, a hypergraph.
no code implementations • 24 Jun 2020 • Eric Bunch, Daniel Dickinson, Jeffery Kline, Glenn Fung
In a more general setting, the magnitude of a metric space is a real number that aims to quantify the effective number of distinct points in the space.