Now showing items 1-3 of 3
Role of Premises in Visual Question Answering
(Virginia Tech, 2017-06-12)
In this work, we make a simple but important observation questions about images often contain premises -- objects and relationships implied by the question -- and that reasoning about premises can help Visual Question ...
Natural Language Driven Image Edits using a Semantic Image Manipulation Language
(Virginia Tech, 2018-06-04)
Language provides us with a powerful tool to articulate and express ourselves! Understanding and harnessing the expressions of natural language can open the doors to a vast array of creative applications. In this work we ...
VIP: Finding Important People in Images
(Virginia Tech, 2015-06-25)
People preserve memories of events such as birthdays, weddings, or vacations by capturing photos, often depicting groups of people. Invariably, some individuals in the image are more important than others given the context ...