I am a fifth year PhD student advised by Devi Parikh at Georgia Tech. I also work closely with Dhruv Batra. Prior to starting my PhD, I was a Research Assistant at the Center for Visual Information Technology (CVIT), IIIT-Hyderabad, India working under the joint supervision of Prof. C.V. Jawahar and Gaurav Sharma. Before moving to Hyderabad, I was a Software Engineer at Media.net in Mumbai, India. I completed my dual degree (B. Tech + M. Tech) in Computer Science and Engineering from IIT Roorkee in 2015.

My research interests are broadly in the intersection of vision, language and actions. I am interested in training AI agents embodied in realsitic simulated environments to perform tasks requiring spatial, semantic and temporal understanding capabilities.


Updates

  • [ Spring 2022 ] Our work on Episodic Memory Question Answering was accepted at CVPR 2022 as an oral presentation! We investigate egocentric personal AI assistants on AR-powered devices (such as smart glasses). Pre-print, code and data coming soon!
  • [ Fall 2021 ] I will be serving as a reviewer for ICLR 2022, CVPR 2022.
  • [ Summer 2021 ] I have passed my PhD proposal at Georgia Tech!
  • [ Fall 2020 ] Our work from my internship at Facebook AI Research on realistic Point-Goal navigation was accepted at CoRL 2020.
  • [ Fall 2020 ] I will be serving as a reviewer for CVPR 2021.
  • [ Summer 2020 ] We were declared as the runners-up in the Point-Goal navigation track of the 2020 Habitat Challenge. This challenge was organized as part of the Embodied AI workshop at CVPR20. Here is a link to the video describing our approach.
  • [ Spring 2020 ] I will be serving as a reviewer for ECCV 2020.
  • [ Summer 2019 ] Our work from my internship at SRI on weakly supervised phrase localization was accepted at ICCV 2019.
  • [ Fall 2019 ] I will be spending the summer interning at Facebook AI Research (FAIR) in Menlo Park, CA.
  • [ Summer 2019 ] I will be serving as a reviewer for NeurIPS 2019.
  • [ Spring 2019 ] Our paper on Embodied Question Answering in Photorealistic Environments with Point-Cloud Perception was accepted as an oral at CVPR 2019.
  • [ Fall 2018 ] I will be spending the summer interning with the Center for Vision Technologies (CVT) group at SRI in Princeton, NJ working on weakly supervised learning for vision and language.
  • [ Fall 2018 ] I am excited to be one of the co-organizers of the NIPS 2018 workshop on Visually Grounded Interaction and Language (ViGIL)
  • [ Fall 2018 ] I will be serving as a reviewer for CVPR 2019.
  • [ Summer 2018 ] I am excited to be one of the co-organizers of the ECCV 2018 workshop on Visual Learning and Embodied Agents in Simulation Environments
  • [ Summer 2018 ] Our paper on "Unsupervised Learning of Face Representations" won the Best Paper Award at FG 2018!
  • [ Spring 2018 ] I am serving as a reviewer for ECCV 2018
  • [ Spring 2018 ] Our paper on Embodied Question Answering has been accepted as an oral at CVPR 2018!
  • [ Spring 2018 ] Our paper on "Unsupervised Learning of Face Representations" has been accepted as an oral at IEEE International Conference on Automatic Face and Gesture Recognition (FG 2018)!
  • [ Fall 2017 ] arXiv paper on Embodied Question Answering is out. Check out the task, dataset and models at embodiedqa.org.
  • [ Summer 2017 ] I presented a lab+tutorial session on "Deep Faces" during the Summer School on Computer Vision (SSCV 2017) at CVIT, IIIT Hyderabad. Here is a link to the GitHub repository that hosts the IPython notebooks.
  • [ Summer 2017 ]: I will be joining the Computer Science PhD program at Georgia Tech, starting Fall 2017!



Publications

Episodic Memory Question Answering
Samyak Datta, Sameer Dharur, Vincent Cartillier, Ruta Desai, Mukul Khanna, Dhruv Batra and Devi Parikh

Computer Vision and Pattern Recognition (CVPR), 2022 (Oral)
Coming soon!


Integrating Egocentric Localization for More Realistic Point-Goal Navigation Agents
Samyak Datta, Oleksandr Maksymets, Judy Hoffman, Stefan Lee, Dhruv Batra and Devi Parikh

Conference on Robot Learning (CoRL), 2020
arxiv


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
arxiv


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)
arxiv


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


Learning OpenCV 3 Application Development

Samyak Datta
Packt Publishers, ISBN 13 : 9781784391454

Build, create and deploy your own computer vision applications with the power of OpenCV.


Thanks to visualdialog.org for the webpage format.