News

I am looking for highly motivated and hard working students. Please read my note and contact me if you are interested in joining my group.

We launched UMN Visual Computing and AI seminar (VCAI). Please stay tuned!

(Sept 2017) Talk "First Person Perception for Robotics" at UMN Center for Cognitive Science.

(Sept 2017) Talk "Learning from First Person Demonstrations" at nVidia research.

(Sept 2017) Talk "Learning from First Person Demonstrations" at JD.com research.

(June 2017) Talk "Learning from First Person Demonstrations" at Egocentric Vision: From Science to Real-World Applications at Indiana University, (slide pdf).

(July 2017) We (with Hanbyul Joo, Tomas Simon, Shohei Nobuhara, and Yaser Sheikh) will give a tutorial on "DIY: A Multiview Camera System" in conjunction with CVPR 2017. We have distinguished invited speakers: Takeo Kanade (CMU), Thabo Beeler/Derek Bradley (Disney Research Zurich), and Christian Theobalt (MPI Informatik). (Tutorial Webpage)

(July 2017) Shan Su will present her work on First Person Basketball Player Prediction in CVPR 2017.

(July 2017) 2 ICCV papers get accepted.

(June 2017) Talk "Learning from First Person Demonstrations" at Egocentric Vision: From Science to Real-World Applications at Indiana University, (slide pdf).

(April 2017) The EgoNet paper with Gedas Bertasius (UPenn), Stella X. Yu (UC Berkeley ICSI), and Jianbo Shi (UPenn) is accepted in RSS 2017.

(Feb 2017) First paper as a PI with Shan Su (UPenn), Jung Pyo Hong (KAIST), and Jianbo Shi (UPenn) on First Person Basketball Player Prediction is accepted as a spotlight presentation to CVPR 2017.

(Feb 2017) Talk at IRIM seminar at GATECH.

(Jan 2017) Talk at Computer Vision seminar at University of Michigan.

(Jan 2017) Talk at Honeywell.

(Dec 2016) DIY: A Multiview Camera System is accepted to CVPR Tutorial 2017.

(Nov 2016) Serving Associate Editor of ICRA 2017.

(Sept 2016) Please meet our social interaction data from the Panoptic Studio. Full 3D body pose, speech, face, hands, and more. We are decoding our social intelligence.

(Aug 2016) Talk at VASC seminar at CMU and Oculus Research Pittsburgh (slide pdf, slide w/ video 1.6Gb).

(May 2016) We demonstrated realtime drone localization (using nVIDIA TK1) appeared on JUNE FIRST Children's day evening gala, CCTV (China Central Television).

(May 2016) The Force from Motion paper will be presented in CVPR 2016 as an oral presentation.

(May 2016) The Future Localization paper will be presented in CVPR 2016 as an oral presentation.

(May 2016) Kris Kitani, Jianbo Shi, and I will give a tutorial in CVPR 2016 on First Person Vision.

(April 2016) New Scientist features our work on EgoNet.

(April 2016) Our lectures on Structure from Motion are online via Coursera Robotics: Perception.

Teaching

    Fall 2017
    Elementray Computational Linear Algebra (CSci 2033)

    Spring 2017
    Multiview 3D Geometry in Computer Vision (CSci 5980/8980) (webpage)

Team

    Shan Su (UPenn PhD program w/ Jianbo Shi)
    Jae Shin Yoon (PhD program)
    Zhixuan Yu (PhD program)
    Yasamin Jafarian (PhD program)
Research Highlight

Joint Attention Social Signal Physical Sensation
Social Saliency Prediction (CVPR 2015)
Social Signal Reconstruction (IJCV 2015)
Force from Motion (CVPR 2016)
3D Joint Attention (NIPS 2012) Motion Capture (SIGGRAPH 2011) Egocentric Future Localization (CVPR 2016)
Social Cameras (SIGGRAPH 2014) Panoptic Studio (CVPR 2014) Basketball Player Prediction (CVPR 2017)

Workshop and Tutorial Organization

Publications

    Customizing First Person Image Through Desired Actions

    S. Shan, J. Shi, and H. S. Park
    arXiv
    Unsupervised Learning of Important Objects from First-Person Videos

    G. Bertasius, H. S. Park, S. X. Yu, and J. Shi
    International Conference on Computer Vision (ICCV) 2017, arXiv
    Am I a Baller? Basketball Performance Assessment using First-Person Cameras

    G. Bertasius, S. X. Yu, H. S. Park, and J. Shi
    International Conference on Computer Vision (ICCV) 2017, arXiv
    First Person Action-Object Detection with EgoNet

    G. Bertasius, H. S. Park, S. X. Yu, and J. Shi
    Robotics: Science and Systems (RSS) 2017, Oral presentation, arXiv
    Predicting Behaviors of Basketball Players from First Person Videos

    S. Su, J. P. Hong, J. Shi, and H. S. Park
    Conference on Computer Vision and Pattern Recognition (CVPR), Spotlight presentation 2017 (webpage), arXiv
    Large-Scale Visual Geo-Localization
    3D Point Cloud Reduction using Mixed-integer Quadratic Programming

    Book chapter, Springer
    Force from Motion: Decoding Physical Sensation from a First Person Video

    H. S. Park, J.-J. Hwang, and J. Shi
    Conference on Computer Vision and Pattern Recognition (CVPR), Oral presentation, 2016 (webpage)

    Force from Motion: Decoding Control Force of Activity in a First Person Video
    H. S. Park and J. Shi (journal version submitted to PAMI pdf)
    Egocentric Future Localization

    H. S. Park, J.-J. Hwang, Y. Niu, and J. Shi
    Conference on Computer Vision and Pattern Recognition (CVPR), Oral presentation, 2016 (webpage)
    Social Saliency Prediction

    H. S. Park and J. Shi
    Conference on Computer Vision and Pattern Recognition (CVPR) Oral presentation, 2015 (webpage)

    Invited paper to Scene Understanding Workshop (in conjunction with CVPR 2015)
    3D Trajectory Reconstruction under Perspective Projection

    H. S. Park, T. Shiratori, I. Matthews, and Y. Sheikh
    International Journal of Computer Vision, 2015 (paper, project page).
    Human Behavior Understanding

    H. S. Park, A. A. Salah, Y. J. Lee, L.-P. Morency, Y. Sheikh, and R. Cucchiara (Eds.)
    Lecture Notes in Computer Science, Springer, 2014
    Social Scene Understanding from Social Cameras

    H. S. Park
    Ph.D. Thesis, Mechanical Engineering Department, Carnegie Mellon University, 2014 (webpage)
    Automatic Editing of Footage from Multiple Social Cameras

    *I. Arev, *H. S. Park, Y. Sheikh, J. Hodgins, and A. Shamir
    ACM Transactions on Graphics (Proc. ACM SIGGRAPH) Oral presentation, 2014 (project page)
    * indicates joint first authors.
    MAP Visibility Estimation for Large-Scale Dynamic 3D Reconstruction

    H. Joo, H. S. Park, and Y. Sheikh
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Oral presentation, 2014 (project page)
    Predicting Primary Gaze Behavior using Social Saliency Fields

    H. S. Park, E. Jain, and Y. Sheikh
    International Conference on Computer Vision (ICCV), 2013 (project page)
    3D Point Cloud Reduction using Mixed-integer Quadratic Programming

    *H. S. Park, *Y. Wang, E. Nurvitadhi, J. C. Hoe, Y. Sheikh, and M. Chen
    Second International Workshop on Visual Analysis and Geo-Localization of Large-Scale Imagery in conjunction with IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Oral presentation, 2013 (project page)
    * Both authors contributed equally to this work.
    3D Social Saliency from Head-mounted Cameras

    H. S. Park, E. Jain, and Y. Sheikh
    Advances in Neural Information Processing Systems (NIPS), 2012 (project page)
    3D Reconstruction of a Smooth Articulated Trajectory from a Monocular Image Sequence

    H. S. Park and Y. Sheikh
    International Conference on Computer Vision (ICCV), 2011 (project page)
    Motion Capture from Body-Mounted Cameras

    T. Shiratori, H. S. Park, L. Sigal, Y. Sheikh, and J. Hodgins
    ACM Transactions on Graphics (Proc. ACM SIGGRAPH) Oral presentation, 2011 (project page)
    3D Reconstruction of a Moving Point from a Series of 2D Projections

    H. S. Park, T. Shiratori, I. Matthews, and Y. Sheikh
    European Conference on Computer Vision (ECCV) Oral presentation, Sept, 2010 (project page)
    Roll and Pitch Motion Analysis of a Biologically Inspired Quadruped Water Runner Robot

    H. S. Park, S. Floyd , and M. Sitti
    International Journal of Robotics Research, December, 2010 (paper)
    Compliant Footpad Design Analysis for a Bio-Inspired Quadruped Amphibious Robot

    H. S. Park and M. Sitti
    IEEE/RSJ International Conference on Intelligent Robots and System (IROS), 2009 (paper)
    Dynamic Modeling and Analysis of Pitch Motion of a Basilisk Lizard Inspired Quadruped Robot Running on Water

    H. S. Park, S. Floyd, and M. Sitti
    2009 International Conference on Robotics and Automation (ICRA), 2009 (paper)
    Dynamic Modeling of a Basilisk Lizard Inspired Quadruped Robot Running on Water

    H. S. Park, S. Floyd, and M. Sitti
    IEEE/RSJ International Conference on Intelligent Robots and System (IROS), 2008 (paper)