Title: Connecting Vision and Language for Interpretation, Grounding, and Imagination

Date: Wednesday, November 29 2017
Time: 12:30PM - 02:30PM (EDT)
Location: CCB 247

Shanmukha Ramakrishna Vedantam
Ph.D. Student
School of Interactive Computing
College of Computing
Georgia Institute of Technology

Committee:
Dr. Devi Parikh (Advisor, School of Interactive Computing, Georgia Institute of Technology)
Dr. Dhruv Batra (School of Interactive Computing, Georgia Institute of Technology)
Dr. Jacob Eisenstein (School of Interactive Computing, Georgia Institute of Technology)
Dr. Kevin P. Murphy (Research Scientist, Google Research)
Dr. C. Lawrence Zitnick (Research Manager, Facebook AI Research)

Abstract:

Understanding how to model computer vision and natural language jointly is a long-standing challenge in artificial intelligence. In this thesis, I will study how modeling vision and language in meaningful ways can derive more human-like inferences from machine learning models. Specifically, I will consider three related problems: interpretation, grounding, and imagination.

In interpretation, the goal will be to get machine learning models to understand an image and describe its contents using natural language in a contextually relevant manner. In grounding, I will study how to connect natural language to referents in the physical world, and show how this can help learn common sense. Finally, in proposed work, I will study how to ‘imagine’ visual concepts completely and accurately across the full range and (potentially unseen) compositions of their visual attributes. I will study these problems from computational as well as algorithmic perspectives and suggest exciting directions for future work.