I am a PhD student in Computer Science at Georgia Tech, advised by Devi Parikh.
ResearchI am interested in understanding and modeling aspects of human behavior in the modalities of vision and language.
I have worked on computational models for human interactions that are typical when interacting with other humans e.g., humor, narrative. I have also worked on understanding human interactions with AI, with the goal of creating better human-AI teams.
My current interests are in understanding embodied human behavior e.g., learning from natural interactions, semantic understanding of human movement, etc.
My work spans the areas of AI, machine learning, computer vision, natural language processing, crowdsourcing and cognitive science.
Do explanation modalities make VQA models more predictable to a human?
Punny Captions: Witty Wordplay in Image Descriptions
Evaluating Visual Conversational Agents via Cooperative Human-AI Games
Sort Story: Sorting Jumbled Images and Captions into Stories
We are Humor Beings: Understanding and Predicting Visual Humor.