In this paper, we study the generation quality of interpolation-based
re...
Many language tasks (e.g., Named Entity Recognition, Part-of-Speech tagg...
Watermarking is a commonly used strategy to protect creators' rights to
...
Existing work on tabular representation learning jointly models tables a...
Cross-Domain Detection (XDD) aims to train an object detector using labe...
While large-scale pretrained language models have significantly improved...
Recent studies indicate that NLU models are prone to rely on shortcut
fe...
We propose D-RISE, a method for generating visual explanations for the
p...
Decomposing images of document pages into high-level semantic regions (e...
Researchers have observed that Visual Question Answering (VQA) models te...
Automatic colorization is the process of adding color to greyscale image...
In recent years, it is common practice to extract fully-connected layer ...
Visual narrative is often a combination of explicit information and judi...
We present a supervised binary encoding scheme for image retrieval that
...