We present a new formulation for structured information extraction (SIE)...
In this work, instead of directly predicting the pixel-level segmentatio...
B-spline models are a powerful way to represent scientific data sets wit...
We present MATrIX - a Modality-Aware Transformer for Information eXtract...
Memorization of the relation between entities in a dataset can lead to
p...
B-spline models are a powerful way to represent scientific data sets wit...
We present Contrastive Neighborhood Alignment (CNA), a manifold learning...
Computer vision applications such as visual relationship detection and
h...
Fitting B-splines to discrete data is especially challenging when the gi...
We address the problem of layout generation for diverse domains such as
...
We study the relationship between catastrophic forgetting and properties...