Krishna Kumar Singh

Research Scientist
Creative Intelligence Lab, Adobe Research
Email: krishsin[at]adobe.com

I am a research scientist at Adobe Research.

I got Phd in Computer Science from University of California, Davis under guidance of Prof. Yong Jae Lee. Previously, I finished my Masters in Robotics at Carnegie Mellon University, advised by Prof. Alexei Efros and Prof. Kayvon Fatahalian. I did undergrad in Computer Science and Engineering at IIIT Hyderabad under supervision of Prof. P J Narayanan.
I was research intern at Intel Labs and was Carnegie Mellon’s Robotics Institute Summer Scholar (RISS) under Prof. Martial Hebert. I also interned at Allen Institute for Artificial Intelligence (AI2) with Dr. Santosh Divvala and Prof. Ali Farhadi. I was a research intern at Facebook AI this summer and worked with Dr. Deepti Ghadiyaram, Dr. Dhruv Mahajan , Dr. Matt Feiszli, and Prof. Kristen Grauman.

My research focuses on developing visual recognition and image generation models with minimal human supervision. Recently, I have been working on unsupervised image generation and disentanglement by providing explicit control over the different fine-grained properties of an image. I am in general interested in generating and disentangling visual data but I am also passionate about other interesting visual recognition problems.

Resume/Linkedin/Google-Scholar

Internship: If you are interested in doing research project with me at Adobe, please send me an email with your resume.

Papers

Don’t Judge an Object by Its Context: Learning to Overcome Contextual Bias
Krishna Kumar Singh, Dhruv Mahajan, Kristen Grauman, Yong Jae Lee, Matt Feiszli, Deepti Ghadiyaram
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Oral Presentation

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation
Yuheng Li, Krishna Kumar Singh, Utkarsh Ojha, Yong Jae Lee
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020

Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Imbalanced Data
Utkarsh Ojha, Krishna Kumar Singh, Cho-Jui Hsieh, Yong Jae Lee
Arxiv, 2019

FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
Krishna Kumar Singh*, Utkarsh Ojha*, Yong Jae Lee
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
* equal contribution
Oral Presentation

You reap what you sow: Using Videos to Generate High Precision Object Proposals for Weakly-supervised Object Detection
Krishna Kumar Singh, Yong Jae Lee
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

DOCK: Detecting Objects by transferring Common-sense Knowledge
Krishna Kumar Singh, Santosh Divvala, Ali Farhadi, Yong Jae Lee
European Conference on Computer Vision (ECCV), 2018

Who Will Share My Image? Predicting the Content Diffusion Path in Online Social Networks
Wenjian Hu, Krishna Kumar Singh*, Fanyi Xiao*, Jinyoung Han, Chen-Nee Chuah, Yong Jae Lee
ACM International Conference on Web Search and Data Mining (WSDM), 2018
* equal contribution

Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization
Krishna Kumar Singh, Yong Jae Lee
International Conference on Computer Vision (ICCV), 2017

Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond
Krishna Kumar Singh, Hao Yu, Aron Sarmasi, Gautam Pradeep, Yong Jae Lee
Arxiv, 2018

Identifying First-Person Camera Wearers in Third-Person Videos
C. Fan, J. Lee, M. Xu, K. K. Singh , Y. J. Lee, D. J. Crandall, and M. S. Ryoo
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

End-to-End Localization and Ranking for Relative Attributes
Krishna Kumar Singh, Yong Jae Lee
European Conference on Computer Vision (ECCV), 2016

Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detection
Krishna Kumar Singh, Fanyi Xiao, Yong Jae Lee
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016

KrishnaCam: Using a Longitudinal, Single-Person, Egocentric Dataset for Scene Understanding Tasks
Krishna Kumar Singh, Kayvon Fatahalian, Alexei A. Efros
Winter Conference on Applications of Computer Vision (WACV), 2016

Storytelling Patches: Predicting Tourist Spots in a City
Aayush Bansal, Krishna Kumar Singh
ECCV Workshop on Storytelling with Images and Videos (VisStory), 2014

Geometry Directed Browser for Personal Photographs
Aditya Deshpande, Siddharth Choudhary, P J Narayanan, Krishna Kumar Singh, Kaustav Kundu, Aditya Singh, Apurva Kumar
ACM Indian Conference On Vision, Graphics And Image Processing (ICVGIP), 2012 (oral presentation)
[Video]

Hybrid Multi-Core Algorithms for Regular Image Filtering Applications
Shrenik Lad, Krishna Kumar Singh, Kishore Kothapalli, P J Narayanan
IEEE International Conference on High Performance Computing (HiPC) Student Research Symposium, 2012 (NVIDIA Best GPU Poster Award) [Poster]

Work Experience


Research Scientist at Adobe Research

Research Intern at Facebook AI (Summer 2019)
Worked on removing contextual bias in visual recognition.

Research Intern at Allen Institute for Artificial Intelligence (Summer 2017)
Worked on improving object detection by transferring common-sense knowledge.
Computer Vision Intern at Intel Labs (Summer 2015)
Worked on Video Summarization and Retrieval. Filed two patents.

Carnegie Mellon’s Robotics Institute Summer Scholar (RISS) under Prof. Martial Hebert (Summer 2012)
Worked on Object Recognition in Different Illumination Conditions. [Poster]