Research
I am currently a postdoc in the Machine Learning and Perception Lab at Virginia Tech working with Dhruv Batra on problems in Computer Vision. My primary interest is the development of models and algorithms capable of making accurate and interpretable inferences in the face of high levels of uncertainty. For more info, see LinkedIn or Google Scholar .
Selected Publications

2017
Viraj Prabhu, Prithvijit Chattopadhyay, Deshraj Yadav, Arjun Chandrasekaran, Abhishek Das, Stefan Lee, Dhruv Batra and Devi Parikh. Evaluating Visual Dialog Agents via Cooperative Human-AI Games. AAAI Conference on Human Computation and Crowdsourcing (HCOMP), 2017.
Qing Sun, Stefan Lee, Dhruv Batra. Bidirectional Beam Search: Forward-Backward Inference in Neural Sequence Models for Fill-in-the-Blank Image Captioning. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [PDF]
Abhishek Das*, Satwik Kottur*, José M. F. Moura, Stefan Lee, Dhruv Batra. Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning. arXiv:1703.06585, 2017. [PDF]
Aroma Mahendru, Viraj Prabhu, Akrit Mohapatra, Dhruv Batra, Stefan Lee. The Promise of Premise: Harnessing Question Premises in Visual Question Answering. Accepted to EMNLP 2017. [PDF]
Satwik Kottur, José M.F. Moura, Stefan Lee, Dhruv Batra. Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog. Accepted to EMNLP 2017. [PDF]
2016
Stefan Lee, Senthil Purushwalkam, Michael Cogswell,Viresh Ranjan, David J. Crandall, and Dhruv Batra. Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles. NIPS 2016. [PDF]
Ashwin K Vijayakumar, Michael Cogswell, Ramprasath R. Selvaraju, Qing Sun, Stefan Lee, David Crandall, Dhruv Batra. Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models. arXiv:1610.02424, 2016 [PDF]
2015
Stefan Lee, Senthil Purushwalkam, Michael Cogswell, David J. Crandall, and Dhruv Batra. Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks. arXiv:1511.06314, 2015. [PDF]
Sven Bambach, Stefan Lee, David Crandall, Chen Yu. Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions. IEEE International Conference on Computer Vision (ICCV), 2015. [PDF] [Dataset WWW] [Paper WWW]
Stefan Lee, Nicolas Maisonneuve, David Crandall, Josef Sivic, Alexei A. Efros. Linking Past to Present: Discovering Style in Two Centuries of Architecture. IEEE International Conference on Computational Photography (ICCP), 2015. [PDF]
Stefan Lee, Haipeng Zhang, David Crandall. Predicting Geo-informative Attributes in Large-scale Image Collections using Convolutional Neural Networks. IEEE Workshop on Applications of Computer Vision (WACV), 2015. [PDF]
Sven Bambach, Stefan Lee, David Crandall, Chen Yu. Detecting and Classifying Hands in Social and Driving Contexts . Vision for Intelligent Vehicles and Applications (VIVA) Challenge and Workshop, IEEE Intelligent Vehicles Symposium, 2015.
Sven Bambach, Stefan Lee, David Crandall, John Franchak, Chen Yu. Tracking Hands of Interacting People in Egocentric Video. Workshop on Observing and Understanding Hands in Action, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
2014
Stefan Lee, Sven Bambach, David Crandall, John Franchak, Chen Yu. This Hand Is My Hand: A Probabilistic Approach to Hand Disambiguation in Egocentric Video. 3rd Workshop on Egocentric Vision, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. (Best Paper Award Winner) [PDF]
Stefan Lee, Jerome Mitchell, David Crandall, and Geoffery Fox. Estimating Bedrock and Surface Layer Boundaries And Confidence Intervals In Ice Sheet Radar Imagery Using MCMC. International Conference on Image Processing, 2014. [PDF]
Stefan Lee and David Crandall. Learning to Identify Local Flora with Human Feedback. Workshop on Computer Vision and Human Computation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. [PDF]

Book Chapters:

David J. Crandall, Yunpeng Li, Stefan Lee, and Daniel P. Huttenlocher. “Recognizing Land- marks in Large-Scale Social Image Collections.” Large-Scale Visual Geo-Localization. Ed. Amir R. Zamir, Asaad Hakeem, Luc Van Gool, Mubarak Shah, Richard Szeliski. Springer, 2016.

Unpublished work possibly of interest to someone somewhere:

A Survey of Sparse Coding for Object Recognition [PDF]
Teaching
Virgina Tech
ECE5424 - Introduction to Machine Learning (Fall 2016)
(Instructor)

Indiana University
B659 - Image Processing and Recognition (Fall 2014)
(Assistant Instructor)
I399 - Research Methods for Informatics and Computing (Fall 2013)
(Graduate Mentor)
C211 - Introduction to Computer Science (Fall 2011 - Summer 2012)
(Assistant Instructor)
Education
PhD in Computer Science (2016)
Advisor: David Crandall
Thesis: Data-Driven Computer Vision for Science and the Humanities

MS in Computer Science (2013)

BS in Computer Science (2011)
About Me
I adore and collect board games and follow an embarrassing number of web comics.

In an effort to balance out the amount of time work keeps me in a chair, I've picked up running and weight lifting. I've played racquetball casually for a number of years but have yet to show any real skill at the game.

One of my favorite perks of academia is the chance to travel and I love visiting new places. I put together a digital push-pin map to keep track of the places I've gone.