I am a Computer Scientist at the Center for Vision Technologies at SRI International, where I primarily work with Ajay Divakaran, Yi Yao and Giedrius Burachas on applying Deep Learning to Computer Vision and Natural Language Processing tasks. I finished graduate school (Master's) majoring in Computer Engineering from Virginia Tech (VT). While at VT, I had the honor of working in the Computer Vision Lab advised by Prof. Devi Parikh and in close collaboration with Prof. Dhruv Batra.
In my research, I am excited about how to make human-AI and AI-AI teams solve tasks effectively. Currently, I am doing so by training machines to understand how the semantics of vision and language intertwine with each other. I believe this is a crucial step for AI's to be able to act effectively in a human-AI or AI-AI collaborative environment.
Dr. Erik Brynjolfsson, the Director of the MIT Center for Digital Business, tweeted:
Drones will soon be able to spot you when you walk around outside: UAV With Facial Recognition Takes Flight http://t.co/qpb2owdzGd— Erik Brynjolfsson (@erikbryn) September 21, 2014
Arijit Ray, Giedrius T. Burachas, Karan Sikka, Anirban Roy, Avi Ziskind, Yi Yao, Ajay Divakaran, Make Up Your Mind: Towards Consistent Answer Predictions in VQA Models [pdf], [bibTex], Workshop on Shortcomings in Vision and Language , European Conference on Computer Vision, 2018
The Art of Deep Connection - Towards Natural and Pragmatic Conversational Agent Interactions. [Master's Thesis], Virginia Tech E-Library, 2017
Prashant Chandrasekar, Xuan Zhang, Saurabh Chakravarty, Arijit Ray, John Krulick, and Alla Rozovskaya, "The Virginia Tech System at CoNLL-2016 Shared Task on Shallow Discourse Parsing", In CoNLL Shared Task (2016).
Object Prediction using Image Context: Predict next object in an image reasoned on present image context in a sequential manner.
Online Demo for Predicting Plausibility of Common Sense Assertions: Enter a three-phrase tuple to assess the plausibility score based on a joint language-vision common-sense reasoning.
Learning to Listen: Matching Cover songs with Original Productions: Match Original Songs to Cover Songs using an Ensemble of Supervised and Unsupervised Approaches.
Ray, Arijit, Kishan Prudhvi Guddanti, and N. Chellammal. "An Approach to Intelligent Traction Control Using Regression Networks and Anomaly Detection." Applied Artificial Intelligence 29.6 (2015): 597-616.
Best way to reach me would be to drop an email to ray93 at vt dot edu. Please don't spam me!