This paper discusses the challenges of optical character recognition (OC...
Recent large-scale text-to-image generation models have made significant...
Videos are created to express emotion, exchange information, and share
e...
We present a novel approach for disentangling the content of a text imag...
A crucial component for the scene text based reasoning required for Text...
Recent advances in OCR have shown that an end-to-end (E2E) training pipe...
We propose real-time, six degrees of freedom (6DoF), 3D face pose estima...
Although a polygon is a more accurate representation than an upright bou...
Recent end-to-end trainable methods for scene text spotting, integrating...
The use of satellite imagery has become increasingly popular for disaste...
A significant number of images shared on social media platforms such as
...
We present the DeepGlobe 2018 Satellite Image Understanding Challenge, w...
This article discusses a framework to support the design and end-to-end
...