Convolutional Neural Networks (CNN) are known to exhibit poor generaliza...
We propose a new method for producing color images from sketches. Curren...
Data shift robustness has been primarily investigated from a fully super...
We introduce a new method for generating color images from sketches or e...
In many real-world problems, there is typically a large discrepancy betw...
Machine learning (ML) systems have introduced significant advances in va...
In this paper, we explore illustrations in children's books as a new dom...
With the introduction of large-scale datasets and deep learning models
c...
This paper is motivated from a young boy's capability to recognize an
il...
We attack the problem of learning face models for public faces from
weak...
Recognizing fonts has become an important task in document analysis, due...
We introduce ConceptVision, a method that aims for high accuracy in
cate...
Unusual events are important as being possible indicators of undesired
c...
We attack the problem of learning concepts automatically from noisy web ...