Abhimanyu Dubey

I am a first-year graduate student at MIT, supervised by Iyad Rahwan. My research interests are in artificial intelligence, computer vision and computational social science. I am supported by an Emerging Worlds Fellowship. Prior to this, I received a master's degree in Computer Science and bachelor's degree in Electrical Engineering at IIT Delhi, where I was supervised by Sumeet Agarwal.

dubeya[at]mit.edu | github | quora | scholar | linkedin


March 2018          Our work on collective intelligence and reinforcement learning has been accepted to IC2S2 2018 as a poster presentation.
February 2018          Quora named me as a Top Writer for 2018!
Our work on collective intelligence and reinforcement learning has been accepted to NetSci 2018 as a spotlight presentation.
January 2018          I will be joining the Computer Vision team at Facebook Research in summer 2018 as a research intern!
December 2017 Our work on understanding the propagation of online imagery has been accepted to WWW 2018! (acceptance rate = 14.8%)
I presented our work on regularizing prediction entropy at the Learning with Limited Data Workshop at NIPS 2017.
November 2017 I will be a TA for the Intro to Deep Learning course at MIT (IAP 2018). Reach out if you wish to enroll!
October 2017 Our paper on modeling image virality was presented at ACM MM 2017.


I am broadly interested in large-scale computer vision and machine learning problems, and their applications to constrained environments with limited, noisy and fine-grained training data. I also enjoy studying the proliferation of imagery in online media using computer vision and collective intelligence. In the past, I have also spent time at the Harvard University Department of Economics, as a post-baccalaureate fellow supervised by Prof. Edward Glaeser, where I worked on predicting housing prices using computer vision; UC Berkeley, as an engineer under Dr. Allen Yang, working on face recognition on handheld devices; MIT Media Lab, under Prof. Ramesh Raskar, where I worked on object tracking and modeling urban perception; Virginia Tech department of ECE, as a summer intern under Prof. Dhruv Batra (now at Georgia Tech), where I worked on large-scale distributed machine learning. At IIT Delhi, I worked under Prof. Sumeet Agarwal, Prof. Jayadeva and Prof. Manik Varma, on various problems in computer vision and machine learning. I also occasionally dabble at writing.


Sparsely-Networked Evolution Strategies for Reinforcement Learning
Dhaval Adjodah, Dan Calacci, Abhimanyu Dubey, Yan Leng, Peter Krafft, Esteban Moro and Alex Pentland
International Conference on Computational Social Science (IC2S2), 2018 (short abstract)
International Conference on Network Science (NetSci), 2018 (spotlight / lightning talk)

Sparse Matching for Embedding Image Macros
Abhimanyu Dubey, Esteban Moro, Manuel Cebrian and Iyad Rahwan
International World Wide Web Conference (WWW), 2018 [pdf]

Regularizing Prediction Entropy Enhances Deep Learning with Limited Data
Abhimanyu Dubey, Otkrist Gupta, Ramesh Raskar, Iyad Rahwan and Nikhil Naik
Workshop on Learning with Limited Data
Neural Information Processing Systems (NIPS), 2017 [pdf]

Modeling Image Virality with Pairwise Spatial Transformer Networks
Abhimanyu Dubey and Sumeet Agarwal
ACM Multimedia Conference (MM), 2017 [pdf]

Deep Learning the City: Quantifying Global Urban Perception
Abhimanyu Dubey, Nikhil Naik, Devi Parikh, Ramesh Raskar and Cesar Hidalgo
European Conference on Computer Vision (ECCV), 2016 [pdf | website]

Examining Representational Similarity in ConvNets and the Primate Visual Cortex
Abhimanyu Dubey, Jayadeva and Sumeet Agarwal
European Conference on Computer Vision (ECCV) Workshops, 2016 (Spotlight) [pdf]

Deep Convolutional Networks for Modeling Image Virality
Abhimanyu Dubey and Sumeet Agarwal
European Conference on Computer Vision (ECCV) Workshops, 2016
Indian Workshop on Machine Learning (iWML), 2016 (Oral) [pdf]

Coreset-Based Adaptive Tracking
Abhimanyu Dubey, Nikhil Naik, Dan Raviv, Rahul Sukthankar and Ramesh Raskar
Preprint 2015 [pdf]

(c) 2018 Abhimanyu Dubey , last updated March 5, 2018. Hits:web counter