Chiho Choi, Ph.D.

I am a at Honda Research Institute USA

News

If you are interested in an internship position for human behavior prediction, please check this link (strong publication record preferred).

  • Mar 2021: "Shared Cross-Modal Trajectory Prediction for Autonomous Driving" is accepted to CVPR 2021 as oral.
  • Feb 2021: "Social-STAGE: Spatio-Temporal Multi-Modal Future Trajectory Forecast" is accepted to ICRA 2021.
  • Nov 2020: "DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning" is accepted to CoRL 2020.
  • Sep 2020: "EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning" is accepted to NeurIPS 2020.
  • Jun 2020: "SSP: Single Shot Future Trajectory Prediction" is accepted to IROS 2020.
  • Apr 2020: "Cooperation-Aware Lane Change Maneuver in Dense Traffic based on Model Predictive Control with Recurrent Neural Network" is accepted to ACC 2020.
  • Feb 2020: "TITAN: Future Forecast using Action Priors" is accepted to CVPR 2020 as oral.
  • In 2019: Papers are accpeted to ICCV, CVPRW, and ICLR.
  • In 2018: I Joined HRI as a Scientist. A paper is accepted to ICRA.

About

I received my Ph.D. in the school of Electrical and Computer Engineering from Purdue University in 2018, where I was advised by Prof. Karthik Ramani. Previously, I received a B.S. from Hanyang University, Korea in 2011, and a M.S. from University of Southern California, in 2013.

  • Work: Honda Research Institute USA, Inc.
  • City: San Jose, CA
  • Title: Scientist
  • Email: chihochoi AT outlook DOT com

 

Research Interests

Computer Vision / Machine Learning / Robotics

My research interests span the fields of computer vision, machine learning, and robotics, focusing on understanding and prediction of human behavior in highly interactive environments. In this area, I build a new perspective for the safe operation of vehicles and robots designed to cooperate with humans.

  • Behavior Reasoning
  • Uncertainty Modeling
  • Motion Prediction
  • Human Pose Prediction
  • Relational Inference
  • Pose Estimation

Facts

436

Citations

23

Papers

18

Patents

33

Collaborators

Resume

Click here to download my full curriculum vitae.

Work Experience

Scientist

Feb 2018 - Present

Honda Research Institute USA, San Jose, CA

  • Leading multiple projects on recognition and prediction of human action, intention, and future behavior
  • Worked on understanding and prediction of human behavior in indoor and outdoor environments
  • Publications in CVPR (oral), ICCV, ACC, ICRA, IROS, CoRL, and NeurIPS

Intern

May 2017 - Aug 2017

HERE Technologies, Chicago, IL

  • Developed a data selection framework generalizable to machine learning systems
  • Worked on large-scale traffic scene understanding for highly automated driving

Education

Ph.D., Electrical & Computer Engineering

Jan 2018

Purdue University, West Lafayette, IN

Specialization: deep learning, 3D vision, recognition, tracking

M.S., Electrical Engineering

May 2013

University of Southern California, Los Angeles, CA

Specialization: 3D shape analysis (matching and registration)

B.S., Electronics & Computer Engineering

Feb 2011

Hanyang University, Seoul, Korea

Minor: Mechanical Engineering

Selected Projects

Dynamic Relational Reasoning

Sep 2019 - Mar 2020
  • Designed relational reasoning graphs that adaptively evolve the dynamics of interaction patterns among heterogeneous agents
  • Role: Project leader
  • J. Li*, F. Yang*, M. Tomizuka, and C. Choi. “EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning”. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) 2020.

Single Shot Future Prediction

Sep 2019 - Mar 2020
  • Proposed a practical trajectory prediction solution for real-time and safety critical applications, running in constant time complexity.
  • Role: Project leader
  • I. Dwivedi, S. Malla, B. Dariush, and C. Choi. “SSP: Single Shot Future Trajectory Prediction”. Proceedings of the IEEE International Conference on Intelligent Robots and Systems (IROS) 2020.

Future Forecast using Action Priors

Jul 2019 - Nov 2019
  • Organized hierarchical action attributes of traffic participants, and explored a role of agents’ actions for future motion prediction
  • Role: Project leader
  • S. Malla, B. Dariush, and C. Choi. “TITAN: Future Forecast using Action Priors”. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020, oral.

Behavior reasoning for Future Forecast

Feb 2019 - May 2019
  • Designed a framework to understand a relationship between intention and behavior. Predicted goal-oriented trajectories of vehicles conditioned on the intention of drivers
  • Role: Project leader / Sole developer
  • C. Choi, S. Malla, A. Patil, and J. H. Choi. “DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning”. Proceedings of the Conference on Robot Learning (CoRL) 2020.

Publications

2020

Shared Cross-Modal Trajectory Prediction for Autonomous Driving
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021, oral, to appear.
C. Choi*, J. H. Choi*, J. Li, S. Malla
arXiv
Social-STAGE: Spatio-Temporal Multi-Modal Future Trajectory Forecast
In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2021, to appear.
S. Malla, C. Choi, and B. Dariush
arXiv
Lane-Change in Dense Traffic with Model Predictive Control and Neural Networks
September 2020.
S. Bae, D. Isele, A. Nakhaei, P. Xu, A. Miranda Anon, C. Choi, K. Fujimura, S. Moura
PDF
EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning
In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) 2020.
J. Li*, F. Yang*, M. Tomizuka, and C. Choi
arXiv Project
SSP: Single Shot Future Trajectory Prediction
In Proceedings of the IEEE International Conference on Intelligent Robots and Systems (IROS) 2020.
I. Dwivedi, S. Malla, B. Dariush, and C. Choi
arXiv
TITAN: Future Forecast using Action Priors
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020, oral.
S. Malla, B. Dariush, and C. Choi
arXiv Dataset

 

2019

Potential Field: Interpretable and Unified Representation for Trajectory Prediction
arXiv preprint arXiv:1911.07414
S. Su, C. Peng, J. Shi, and C. Choi
arXiv
NEMO: Future Object Localization Using Noisy Ego Priors
arXiv preprint arXiv:1909.08150
S. Malla, I. Dwivedi, B. Dariush, and C. Choi
arXiv Dataset
Cooperation-Aware Lane Change Maneuver in Dense Traffic based on Model Predictive Control with Recurrent Neural Network
In Proceedings of the American Control Conference (ACC) 2020.
S. Bae, D. Saxena, A. Nakhaei, C. Choi, K. Fujimura, and S. Moura
arXiv
DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning
In Proceedings of the Conference on Robot Learning (CoRL) 2020.
C. Choi, S. Malla, A. Patil, and J. H. Choi
arXiv Video
Looking to Relations for Future Trajectory Forecast
In Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2019.
C. Choi and B. Dariush
arXiv Magazine
Learning to Infer Relations for Future Trajectory Forecast
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2019.
C. Choi and B. Dariush
PDF Poster
Deep Learning 3D Shapes Using Alt-az Anisotropic 2-Sphere Convolution
In Proceedings of the International Conference on Learning Representations (ICLR) 2019.
M. Liu, F. Yao, C. Choi, A. Sinha, and K. Ramani
PDF

 

2018

Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems
In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2019.
Y. Yao, M. Xu, C. Choi, D. Crandall, E. Atkins, and B. Dariush
arXiv Code Dataset News
Computational Learning for Hand Pose Estimation
Ph.D. Dissertation, Purdue University, Jan 2018.
C. Choi
e-Pub

 

2017

Learning Hand Articulations by Hallucinating Heat Distribution
In Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2017.
C. Choi, S. Kim, and K. Ramani
PDF Supplementary
Robust Hand Pose Estimation during the Interaction with an Unknown Object
In Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2017.
C. Choi, S. H. Yoon, C. N. Chen, and K. Ramani
PDF Supplementary
Embedding Compressive Layers in Deep Neural Networks
Purdue C-Design Lab Technical Report, May 2017.
C. Choi, S. Kim, J. H. Choi, and K. Ramani
PDF

 

2016

DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed with Deep Features
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016.
A. Sinha*, C. Choi*, and K. Ramani
PDF Supplemenatry Video News Interview Blog

 

2015

A Collaborative Filtering Approach to Real-time Hand Pose Estimation
In Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2015.
C. Choi, A. Sinha, J. H. Choi, S. Jang, and K. Ramani
PDF Supplementary Video

 

2013

Dense and Reliable Shape Matching using 3D Particle Filtering
USC CGIT Lab Technical Report, May 2013.
C. Choi and S. You

 

* co-first author

Academic Services

Program Committee / Reviewer

  • IEEE International Conference on Computer Vision (ICCV) 2019, 2021
  • International Conference on Machine Learning (ICML) 2021
  • The IEEE Robotics and Automation Letters 2021
  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 2019, 2020, 2021
  • Association for Advancement of Artificial Intelligence (AAAI) 2020, 2021
  • International Conference on Learning Representations (ICLR), 2021
  • IEEE Winter Conference on Applications of Computer Vision (WACV), 2021
  • Asian Conference on Computer Vision (ACCV) 2018, 2020
  • Advances in Neural Information Processing Systems (NeurIPS), 2020
  • European Conference on Computer Vision (ECCV), 2020
  • IEEE Intelligent Vehicles Symposium, 2020
  • IEEE Transactions on Intelligent Vehicles, 2020
  • ACM CHI Conference on Human Factors in Computing Systems LBW, 2019
  • IEEE Transactions on Image Processing, 2018
  • IEEE Transactions on Multimedia, 2017