Using Neural Networks to Generate Image Captions

Add to your list(s) Download to your calendar using vCal

• Tudor Mihai Avram, Homerton College
• Wednesday 15 February 2017, 19:30-20:00
• Wolfson Hall, Churchill College.

If you have a question about this talk, please contact Matthew Ireland.

Even since the start of artificial intelligence, computer vision has been an area of interest for researchers all around the globe. Studies going as far as the 1970s form the base of the algorithms that we use today. Automatically describing the contents of an image is a fundamental challenge in artificial intelligence that connects both computer vision and natural language processing. It has applications in many fields, for instance helping visual impaired people or even for education purposes. In this talk, I will describe the algorithms used in the open-source solution implemented in TensorFlow. I will also do a short demonstration of the library, using an application I developed.

This talk is part of the Churchill CompSci Talks series.

This talk is included in these lists:

• Churchill CompSci Talks
• Wolfson Hall, Churchill College
• computer science
• se393's list

Note that ex-directory lists are not shown.