Abstract
The ability to associate images with natural language sentences that describe what is depicted in
them is a hallmark of image understanding, and a prerequisite for applications such as
sentence-based image search. The purpose of this tutorial is to give researchers in computer vision an overview of the issues involved in automatic image description, and to
introduce them to natural language processing tools and ideas they can use for this purpose.
Slides
Part 1
Part 2
For a similar tutorial (including slides) to a natural language processing audience, see our
EACL 2014 tutorial.