I am Abhishek Das, a Computer Science PhD student at Georgia Tech, advised by Prof. Dhruv Batra. My research focuses on deep learning models and its applications in computer vision and natural language processing. Before transferring to Georgia Tech, I spent one year at Virginia Tech as an intern and later as a graduate student working with Prof. Dhruv Batra and Prof. Devi Parikh.
I graduated from Indian Institute of Technology Roorkee in 2015. During my undergrad years, I’ve been selected twice for Google Summer of Code (2013 and 2014), won several hackathons and security contests (Yahoo! HackU!, Microsoft Code.Fun.Do., Deloitte CCTC 2013 and 2014), and been an active member of SDSLabs.
On the side, I built neural-vqa, an efficient Torch implementation for visual question answering, and maintain aideadlin.es, which is a website that hosts countdowns to a bunch of CV/NLP/ML/AI conference deadlines, and several other side projects (HackFlowy, graf, etc). I also help maintain Erdős, a competitive math learning platform I created during my undergrad. I often tweet, and post pictures from my travels on Instagram and Tumblr.
Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization
NIPS 2016 Interpretable ML for Complex Systems Workshop
Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?
EMNLP 2016, ICML 2016 Workshop on Visualization for Deep Learning
ICML 2016 Workshop on Visualization for Deep Learning
AirMaps was a fun hackathon project that lets users navigate through Google Earth with gestures and speech commands using a Kinect sensor. It was the winning entry in Microsoft Code.Fun.Do.
Another fun hackathon-winning project built during Yahoo! HackU! 2012 that involves webRTC-based P2P video chat, and was faster than any other video chat provider (at the time, before Google launched Hangouts).
Ugly-looking, but super-effective bash script for downloading entire playlists from 8tracks. (Still works as of 10/2016).