Ryo Yonetani

Ryo Yonetani

Interests
  • Computer Vision (Visual Forecasting, First-Person Vision)
  • Machine Learning (Federated Learning, Robot Learning)
Education
  • Ph.D in Informatics, 2013

    Kyoto University

  • M.S in Informatics, 2010

    Kyoto University

  • B.E in Electrical and Electronic Engineering, 2008

    Kyoto University

Experience

 
 
 
 
 
Project Assistant Professor
Apr 2021 – Present Tokyo, Japan
 
 
 
 
 
Principal Investigator
Apr 2020 – Present Tokyo, Japan
 
 
 
 
 
Senior Researcher
Jan 2018 – Dec 2019 Tokyo, Japan
 
 
 
 
 
Visiting Scholar
Sep 2016 – Aug 2017 Pittsburgh, CA, USA
 
 
 
 
 
Assistant Professor
Apr 2014 – Dec 2018 Tokyo, Japan

Projects

Activity Forecasting
Forecasting trajectories of pedestrians in videos
Decentralized Learning
Learning deep neural networks efficiently from decentralized and heterogeneous data
First Person Vision
Analyzing human activities using a collection of wearable cameras

Publications

(2020). Path Planning using Neural A* Search. CoRR.

PDF Cite

(2020). Crowd Density Forecasting by Modeling Patch-based Dynamics. IEEE Robotics and Automation Letters (RA-L).

PDF Cite DOI

(2020). Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data. Proceedings of the IEEE International Conference on Communications (ICC).

PDF Cite DOI

(2020). L2B: Learning to Balance the Safety-Efficiency Trade-off in Interactive Crowd-aware Robot Navigation. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

PDF Cite

(2020). MGpi: A Computational Model of Multiagent Group Perception and Interaction. Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS).

PDF Cite

(2020). MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI).

PDF Cite DOI

(2020). Support Strategies for Remote Guides in Assisting People with Visual Impairments for Effective Indoor Navigation. Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI).

PDF Cite DOI

(2020). Adaptive Distillation for Decentralized Learning from Heterogeneous Clients. Proceedings of the International Conference on Pattern Recognition (ICPR).

PDF Cite

(2019). Decentralized Learning of Generative Adversarial Networks from Multi-Client Non-iid Data. CoRR.

PDF Cite

(2019). Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge. Proceedings of the IEEE International Conference on Communications, (ICC).

PDF Cite DOI

(2019). Assisting group activity analysis through hand detection and identification in multiple egocentric videos. Proceedings of the International Conference on Intelligent User Interfaces (IUI).

PDF Cite DOI

(2018). Browsing Group First-Person Videos with 3D Visualization. Proceedings of the ACM International Conference on Interactive Surfaces and Spaces (ISS).

PDF Cite DOI

(2018). Dynamic Object Scanning: Object-Based Elastic Timeline for Quickly Browsing First-Person Videos. Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI-EA).

PDF Cite DOI

(2018). Ego-Surfing: Person Localization in First-Person Videos Using Ego-Motion Signatures. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

PDF Cite DOI

(2018). Exploring the Role of Tunnel Vision Simulation in the Design Cycle of Accessible Interfaces. Proceedings of the Web for All Conference (W4A).

PDF Cite DOI

(2018). Future Person Localization in First-Person Videos. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

PDF Cite DOI

(2017). Temporal Localization and Spatial Segmentation of Joint Attention in Multiple First-Person Videos. Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW).

PDF Cite DOI

(2017). EgoScanning: Quickly Scanning First-Person Videos with Egocentric Elastic Timelines. Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI).

PDF Cite DOI

(2017). Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption. Proceedings of the IEEE International Conference on Computer Vision (ICCV).

PDF Cite DOI

(2017). Rapid Prototyping of Accessible Interfaces With Gaze-Contingent Tunnel Vision Simulation. Proceedings of the International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS).

PDF Cite DOI

(2017). Egoscanning: quickly scanning first-person videos with egocentric elastic timelines. Proceedings of the SIGGRAPH Asia Emerging Technologies.

PDF Cite DOI

(2016). Discovering Objects of Joint Attention via First-Person Sensing. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

PDF Cite DOI

(2016). Recognizing Micro-Actions and Reactions from Paired Egocentric Videos. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

PDF Cite DOI

(2016). Visual Motif Discovery via First-Person Vision. Proceedings of the European Conference on Computer Vision (ECCV).

PDF Cite DOI

(2016). Can Eye Help You?: Effects of Visualizing Eye Fixations on Remote Collaboration Scenarios for Physical Tasks. Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI).

PDF Cite DOI

(2015). Ego-surfing first person videos. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

PDF Cite DOI

(2013). Predicting where we look from spatiotemporal gaps. Proceedings of the International Conference on Multimodal Interaction (ICMI).

PDF Cite DOI

(2013). Computational Models of Human Visual Attention and Their Implementations: A Survey. IEICE Transactions on Information and Systems.

PDF Cite DOI

(2013). Learning aspects of interest from Gaze. Proceedings of the workshop on Eye gaze in intelligent human machine interaction: gaze in multimodal interaction (GazeIn@ICMI).

PDF Cite DOI

(2013). Learning Spatiotemporal Gaps between Where We Look and What We Focus on. IPSJ Transactions on Computer Vision and Applications.

PDF Cite DOI

(2012). Mental Focus Analysis Using the Spatio-temporal Correlation between Visual Saliency and Eye Movements. Journal of Information Processing.

PDF Cite DOI

(2012). Modeling video viewing behaviors for viewer state estimation. Proceedings of the ACM Multimedia Conference (ACMMM).

PDF Cite DOI

(2012). Multi-mode saliency dynamics model for analyzing gaze and attention. Proceedings of the Symposium on Eye-Tracking Research and Applications (ETRA).

PDF Cite DOI

(2012). Single Image Segmentation with Estimated Depth. Proceedings of the British Machine Vision Conference (BMVC).

PDF Cite DOI

(2010). Gaze Probing: Event-Based Estimation of Objects Being Focused On. Proceedings of the International Conference on Pattern Recognition (ICPR).

PDF Cite DOI

Academic Activities

Awards

  • Outstanding Reviewer @ CVPR2017
  • IBM Best Student Paper Award (Track IV: Biometrics and Human Computer Interaction) @ ICPR2010
  • Other 5 awards in Japan

Grants

  • JST ACT-I “Privacy-Preserving First-Person Vision”, 2016 - 2018 (PI)
  • Foundation for the Promotion of Industrial Science Scholarship Program, 2016 - 2017
  • JSPS Grant-in-Aid for Young Scientists (B), 2015 - 2017 (PI)
  • The Kayamori Foundation for Informational Science Advancement Research Grant, 2015 - 2017 (PI)
  • The Okawa Foundation for Information and Telecommunications Research Grant, 2015 - 2016 (PI)
  • JST CREST “Analyzing Human Attention and Behavior via Collective Visual Sensing for the Creation of Life Innovation”, 2014 - 2018 (Collaborator)
  • JST SICORP “Learning and Detecting Changes in Population Behavior from Video”, 2017 - 2018 (Collaborator)
  • JSPS Research Fellowship for Young Scientists (JSPS DC2), 2012 - 2014 (PI)
  • Young Leader Fostering Program, supported by Kyoto University Global COE program, 2011 - 2012 (PI)

Conference Experience

Chairs

Reviewers

  • Computer vision: CVPR (2015 - Present), ICCV (2015 - Present), ECCV (2014 - Present), ACCV (2014 - Present), IEEE TPAMI, IJCV
  • Robotics: ICRA (2019 - Present), IROS (2019 - Present)
  • Machine learning and AI: IJCAI (2021 as a Senior Program Chair)
  • Others: CHI (2017), ICPR (2014)