Michael S. Ryoo
Assistant Professor
Department of Computer Science and Informatics
School of Informatics and Computing
Indiana University Bloomington


old JPL website

I am an Assistant Professor of the School of Informatics and Computing at Indiana University. I also am affiliated with the NASA's Jet Propulsion Laboratory (JPL), California Institute of Technology as their Research Affiliate. Before joining IU, I was a Research Technologist within the Robotics Section of JPL from October 2011 to July 2015. Prior to that, I completed my national duty at ETRI, Korea, working as a research scientist. I received my Ph.D. from the University of Texas at Austin in 2008, and the B.S. degree from the Korea Advanced Institute of Science and Technology (KAIST) in 2004.

***JPL First-Person Interaction dataset (JPL-Interaction dataset) got updated to include our HRI 2015 videos.***
***DogCentric Activity dataset is now available! It is a new first-person video dataset taken with dogs.***

Recent News
2016/09: A new (updated) paper on activity recognition from extreme low resolution (e.g., 16x12) videos for privacy-preserving computer vision:
Privacy-Preserving Human Activity Recognition from Extreme Low Resolution
2016/05: A new paper on end-to-end learning of human activities and their latent sub-events to enable better activity recognition:
Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters
2016/05: Won the Best Vision Paper Award from ICRA 2016. This is based on the paper Multi-Type Activity Recognition in Robot-Centric Scenarios with Ilaria Gori, J.K. Aggarwal, and Larry Matthies.
2016/03: We (me, Kris Kitani at CMU, Yong Jae Lee at UC Davis, and Yin Li at Gatech) will be organizing the 4th workshop on
Egocentric (First-Person) Vision at CVPR 2016.
2015/06: My paper on new feature representation for first-person videos appeared at CVPR 2015:
Pooled Motion Features for First-Person Videos [source code]
2015/03: My robot-centric activity prediction paper at HRI 2015 was one of the two nominees for their Best Enabling Technology Award:
Robot-Centric Activity Prediction from First-Person Videos: What Will They Do to Me?

Curriculum Vitae pdf

Publications [by topic] [by type] [by year]

List of selected recent publications

  • M. S. Ryoo, B. Rothrock, and L. Matthies, "Pooled Motion Features for First-Person Videos", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015. [arXiv preprint] [source code]
  • M. S. Ryoo, T. J. Fuchs, L. Xia, J. K. Aggarwal, and L. Matthies, "Robot-Centric Activity Prediction from First-Person Videos: What Will They Do to Me?", ACM/IEEE International Conference on Human-Robot Interaction (HRI), March 2015 (full paper). pdf dataset
  • M. S. Ryoo and L. Matthies, "First-Person Activity Recognition: What Are They Doing to Me?", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2013. pdf video dataset
  • M. S. Ryoo, "Human Activity Prediction: Early Recognition of Ongoing Activities from Streaming Videos", International Conference on Computer Vision (ICCV), Barcelona, Spain, November 2011. pdf results
  • M. S. Ryoo and J. K. Aggarwal, "Stochastic Representation and Recognition of High-level Group Activities", International Journal of Computer Vision (IJCV), 93(2):183-200, June 2011. pdf link
  • M. S. Ryoo and J. K Aggarwal, "Spatio-Temporal Relationship Match: Video Structure Comparison for Recognition of Complex Human Activities", International Conference on Computer Vision (ICCV), Kyoto, Japan, October 2009. pdf
Google Scholar page: Google Scholar: Michael S. Ryoo

Lab members

AJ Piergiovanni (PhD student)
Alex Seewald (PhD student)
Jangwon Lee (PhD student, co-advised with Selma Sabanovic and David Crandall)
Maria Soledad Elli (MS student)


I590/B659: Vision for Intelligent Robotics (Fall 2016)
I400/B490: Introduction to Computer Vision (Spring 2016)
I590/B659: Vision for Intelligent Robotics (Fall 2015)

Updated 09/21/2016