Hi! I am a fifth year Ph.D. student at the Computer Vision Lab, Georgia Tech. My advisor is Devi Parikh. I am broadly interested in computer vision and machine learning. My research is supported by a Google PhD fellowship in Machine Perception, Speech Technology and Computer Vision. I am graduating in 2018 and am on the job market.
On the vision side, I am interested in problems in vision and language, learning common sense and visual reasoning. On the machine learning side, I am interested in developing tools for effective low-shot learning, generative models, bayesian deep learning and variational inference.
I also care about issues of how we evaluate our models, as we edge towards higher-level AI-complete tasks. In my first project in grad school, I worked on a (now popularly used) evaluation metric for image captioning called CIDEr.
- [April, 2018] I received the 2018 Google PhD Fellowship in Machine Perception, Speech Technology and Computer Vision!
- [March, 2018] I will be interning at MSR Cambridge this summer, working on generative models of vision, language and action!
- [Feb, 2018] Paper on learning grounded generative (image) models accepted to ICLR, 2018!
- [August, 2017] I will be moving to Georgia Tech this Fall, following my advisor's move!
- [June, 2017] Recognized as one of the outstanding reviewers at CVPR, 2017
- [June, 2017] Paper on learning word embeddings grounded in sounds accepted as a short paper at EMNLP, 2017!
- [May, 2017] I interned at Facebook AI Research (FAIR) in Summer, 2017, working with Devi Parikh, Dhruv Batra and Marcus Rohrbach!
- [March, 2017] Two papers accepted to CVPR 2017 as Spotlight presentations!
- [Jan, 2017] I interned at Google Research in Winter 2017, working with Kevin Murphy on generative models for images!
- [May, 2016] I interned at Google Research in Summer 2016, with Gal Chechik and Samy Bengio!
- MSCOCO Caption Evaluation code
- Codes from MSCOCO Caption Evaluation for metrics (BLEU, ROUGE, CIDEr-D and METEOR), independent of the COCO annotations
- Code for our CVPR'16 paper on Learning Visually Grounded Word Embeddings
- Code for our ICLR'18 paper on Generative Models of Visually Grounded Imagination
If you like this layout/page, see this to build your own using github+jekyll