Christopher Funk, Ph.D.

Senior R&D Engineer

Christopher Funk, Ph.D., is an R&D engineer on Kitware’s Computer Vision Team located in Arlington, Virginia. He has experience working in multiple modalities, including image, video, remote sensing, motion capture, foot pressure, and medical data (e.g. electroencephalogram, or EEG). 

Chris is primarily involved in computer vision/machine learning projects.  He leads the two Defense Advanced Research Projects Agency (DARPA) projects, Learning with Less Labels and SAIL-ON Novelty Detection. For the Learning with Less Labels project, he led the creation of a unified framework for image classification, object recognition, and machine translation that integrates with the program’s test and evaluation. The framework has been generalized to multiple projects, now called Tinker, with a focus on simplifying researchers’ integration, ease of running multiple experiments, and moving to production.  It has also become the primary framework for SAIL-ON. 

Chris is also actively involved in writing proposals, including the successful DARPA SAFE-SiM proposal worth $1.2M in Phase 1 and the National Institutes of Health (NIH) Medical Image Quality Assessment (MIQA) proposal worth $1.6M. 

In 2017, Chris helped run the Conference on Computer Vision and Pattern Recognition (CVPR). In the same year, he also helped run the symmetry competition workshop at the International Conference on Computer Vision (ICCV). His work has been published in CVPR and ICCV proceedings. More recently, he also created the official visualization for finding papers at CVPR 2020 and 2021.   

While working on his Ph.D., Chris was a teaching assistant for computer vision, pattern recognition and machine learning, computer graphics, and computational symmetry courses. He also worked with machine learning tasks, such as developing the first deep learning-based reflection and rotation symmetry detection approaches. These approaches mimicked human symmetry perception in a real-world, unconstrained setting. He also developed the symmetry dataset by creating an Amazon Mechanical Turk using Django from scratch. 

During this time, Chris also analyzed EEG data to understand how the human brain processes symmetry groups. He discovered a connection between human perception and the mathematical perception of symmetry groups. He also developed the first foot pressure estimation algorithm that uses an image to predict a human’s balance. Chris also gained experience working with many texture detection, transfer, and synthesis approaches using classical methods and generative adversarial networks (GANs). 

In 2018, Chris received his Ph.D. in computer science from Penn State University. His thesis focused on detecting symmetry in images and how symmetry is detected within the human brain. He received his master’s degree in computer science from Pace University in 2013. During his studies, he took a cognitive approach to computer vision and worked with architectures such as Soar and physics engines like PhysX to learn to predict future object positions. Chris received his bachelor’s degree in government from Franklin & Marshall College in 2010.

Education

Ph.D. in computer science and engineering from The Pennsylvania State University, 2018

M.S. in computer science from Pace University, 2013

B.S. in government from Franklin & Marshall College, 2010

 

Awards

Best Research Project, Pace University Computer Science Research Day, 2013

Best Graduate Student, Pace University Computer Science Department, 2013

Invited Talks & External Recognition

  • “WEFT Feature Detection and Mensuration for Airplane Classification in Satellite Imagery,” oral presentation, MSS National Symposium on Sensor and Data Fusion, 2019
  • “Beyond Planar Symmetry,” oral presentation for ICCV, 2017
  • “Symmetry Competition Workshop: Evaluation and Results,” oral presentation, ICCV Workshops, 2017 
  • “4D Model-Based Spatiotemporal Alignment of Scripted Taiji Quan Sequences,” poster presentation, ICCV Workshops, 2017
  • “Symmetry reCAPTCHA,” poster presentation, CVPR, 2016 
  • “LabelMeSymmetry: a tool for human symmetry perception,” poster presentation, Vision Sciences Society (VSS), 2016

Get to Know Chris

What is your favorite thing about working at Kitware? The variety of work, from working on computer vision problems on hard government datasets to exploring HPC machine learning projects where each datum is over a terabyte, there is a large variety of work where I can contribute. 

Share something interesting about yourself that is not on your resume. Some of my hobbies include cooking, playing video games, and going to museums.

Professional Associations & Service

  • Member, IEEE Computer Society, 2013-present
  • Member, Computer Vision Foundation (CVF), 2016-present
  • Program committee member, Computer Vision and Pattern Recognition (CVPR)
  • Program committee member, European Conference on Computer Vision (ECCV) 
  • Program committee member, International Conference on Computer Vision (ICCV) 
  • Program committee member, IEEE Winter Conference on Applications of Computer Vision (WACV)
  • Program committee member, British Machine Vision Conference (BMVC)
  • Program committee member, Asian Conference on Computer Vision (ACCV)
  • Program committee member, Association for the Advancement of Artificial Intelligence (AAAI)

 

Publications

Chris’ publication list is below. To see all of Kitware’s computer vision publications, please visit the Computer Vision Publications page.

  1. J. Scott, B. Ravichandran, C. Funk, R. Collins, and Y. Liu, "From Image to Stability: Learning Dynamics from Human Pose," in European Conference on Computer Vision 2020, 2020.
  2. C. Funk, J. Crall, W. Hicks, C. Law, P. Tunison, R. Blue, A. Hoogs, T. Rovito, and A. Maltenfort, "WEFT Feature Detection and Mensuration for Airplane Classification in Satellite Imagery," in MSS National Symposium on Sensor and Data Fusion, 2019.
  3. C. Funk, S. Nagendra, J. Scott, B. Ravichandran, J. Challis, R. Collins, and Y. Liu, "Learning Dynamics from Kinematics: Estimating 2D Foot Pressure Maps from Video Frames," arXiv preprint arXiv:1811.12607, Nov. 2018. [URL]
  4. C. Funk, S. Lee, M. Oswald, S. Tsogkas, W. Shen, A. Cohen, S. Dickinson, and Y. Liu, "2017 ICCV Challenge: Detecting Symmetry in the Wild," in 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017. [URL]
  5. J. Scott, R. Collins, C. Funk, and Y. Liu, "4D Model-Based Spatiotemporal Alignment of Scripted Taiji Quan Sequences," in 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017. [URL]
  6. C. Funk and Y. Liu, "Beyond Planar Symmetry: Modeling Human Perception of Reflection and Rotation Symmetries in the Wild," in Proceedings of the IEEE International Conference on Computer Vision, 2017. [URL]
  7. C. Funk and Y. Liu, "LabelMeSymmetry: a tool for human symmetry perception," Journal of Vision, vol. 16, no. 12, pp. 306, Sep. 2016. [URL]
  8. C. Funk and Y. Liu, "Symmetry reCAPTCHA," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. [URL]

Bibliography generated 2021-03-09-07:00:12 (4470)