profile picture

I am a third year PhD student advised by Prof. Devi Parikh in the School of Interactive Computing within the College of Computing at Georgia Tech. I also work closely with Prof. Dhruv Batra. Prior to starting my PhD, I was a Research Assistant at the Center for Visual Information Technology (CVIT), IIIT-Hyderabad working under the joint supervision of Prof. C.V. Jawahar and Prof. Gaurav Sharma. Before moving to Hyderabad, I was a Software Engineer at in Mumbai. I completed my dual degree (B. Tech + M. Tech) in Computer Science and Engineering from IIT Roorkee in 2015. Over the course of my undergrad, I spent 3 wonderful summers at Google India, and Cadence Design Systems working on projects ranging from Machine Learning, Natural Language Processing to building web-based products.

Broadly speaking, my area of interests lie at the intersection of vision, language and actions. I am interested in training embodied agents to solve high-level AI tasks such as visual navigation and question-answering in simulation environments. I have also worked on problems in the space of weakly supervised learning.


Email | GitHub



Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment
Samyak Datta, Karan Sikka, Anirban Roy, Karuna Ahuja, Devi Parikh and Ajay Divakaran International Conference on Computer Vision (ICCV), 2019


Embodied Question Answering in Photorealistic Environments with Point Cloud Perception
Erik Wijmans* , Samyak Datta*, Oleksandr Maksymets* , Abhishek Das , Georgia Gkioxari, Stefan Lee, Irfan Essa, Devi Parikh and Dhruv Batra
Computer Vision and Pattern Recognition (CVPR), 2019 (Oral)


Embodied Question Answering
Abhishek Das , Samyak Datta, Georgia Gkioxari, Stefan Lee, Devi Parikh and Dhruv Batra
Computer Vision and Pattern Recognition (CVPR), 2018 (Oral)
arxiv / project page

Unsupervised Faces

Unsupervised Learning of Face Representations
Samyak Datta, Gaurav Sharma and C.V. Jawahar
IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2018 (Oral)
Best Paper Award


Integrating Geometric and Textural Features for Facial Emotion Classification using SVM Frameworks
Samyak Datta, Debashis Sen, R. Balasubramanian
International Conference on Computer Vision and Image Processing (CVIP), 2016


SRI International
Research Intern, May 2018 - August 2018

Worked as part of the Computer Vision Technologies Group on problems in the area of weakly supervised multi-modal matching of images and text. (More details coming soon) (Directi)
Software Engineering Intern, May 2014 - July 2014

Worked on a language-processing project that involved extracting semantic entities out of compound and noisy domain names. Most of the domain names are compound words where the constituent words are noisy due to the presence of deliberate spelling errors (e.g. I designed and deployed an algorithm that produces a viable split, given such a compound and noisy input.

Google (India)

Google (India)
Software Engineering Intern, May 2013 - July 2013

Worked on graph-based clustering algorithms. The clustering was run on Google’s Knowledge Graph and the resulting entity-clusters were used for personalized search query suggestions - if the user is interested in topic X, then (s)he may also be interested in other topics from the same cluster.

Cadence Design Systems

Cadence Design Systems
Summer Trainee, May 2012 - July 2012

Worked with the I.T. Automation team of Cadence Design Systems, India Pvt. Ltd and developed a Function Point (FP) Estimation Tool using PHP and MySQL which performed the FP Estimation of the projects undertaken by Cadence.