Arjun Chandrasekaran

arjun9@gatech.edu | CV | Google Scholar

I am a PhD student in Computer Science at Georgia Tech, advised by Devi Parikh.

I have also spent summers interning at Toyota Technological Institute in Chicago (TTIC), Facebook AI Research (FAIR) and Indiana University's Dept. of Psychological and Brain Sciences.

Non-research stuff that I'm interested in.



Research

I 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.

Publications

Do explanation modalities make VQA models more predictable to a human?
A. Chandrasekaran*, V. Prabhu*, D. Yadav*, P. Chattopadhyay*, D. Parikh (*Equal contribution)
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018.

Punny Captions: Witty Wordplay in Image Descriptions
A. Chandrasekaran, D. Parikh, M. Bansal
North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT), 2018.
[Data: Pun vocab (python pickle)]      [Human witty captions]

It Takes Two to Tango: Towards Theory of AI’s Mind
A. Chandrasekaran*, D. Yadav*, P. Chattopadhyay*, V. Prabhu*, D. Parikh
Chalearn Looking at People Workshop, (CVPR), 2017.
[Demo]    [Code]

Evaluating Visual Conversational Agents via Cooperative Human-AI Games
P. Chattopadhyay*, D. Yadav*, V. Prabhu, A. Chandrasekaran, A. Das, S. Lee, D. Batra, D. Parikh (*Equal contribution)
AAAI Conference on Human Computation and Crowdsourcing (HCOMP), 2017.
[Code]

Sort Story: Sorting Jumbled Images and Captions into Stories
H. Agrawal*, A. Chandrasekaran*, D. Batra, D. Parikh, M. Bansal (*Equal contribution)
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2016.
[Podcast Interview]

We are Humor Beings: Understanding and Predicting Visual Humor.
A. Chandrasekaran, A. Kalyan, S. Antol, M. Bansal, D. Batra, C. L. Zitnick, D. Parikh
Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (Spotlight).
[Download data]    [Browse funny scenes]    [Browse funny-unfunny pairs]    [Spotlight talk]    [Create abstract scenes]
Media Coverage: MIT Technology Review, Newsweek, Virginia Tech ECE News