I am a Senior Researcher at the Visual Intelligence Lab, ETRI (Electronics and Telecommunications Research Institute), where I have been working since 2019.

I am also a Ph.D. student in the School of Electrical Engineering at KAIST, advised by Prof. Changick Kim at the Computational Imaging Lab.

My research focuses on video and multimodal intelligence for understanding and forecasting dynamic environments. I develop models that go beyond recognizing what is happening to anticipate future human behavior, vehicle motion, and traffic interactions. My work integrates vision-language learning, motion forecasting, and infrastructure-based visual intelligence toward safer and more intelligent transportation systems.

Video Understanding & Future Behavior Forecasting
Multimodal Learning & Vision-Language Models
Human and Vehicle Behavior Prediction
Intelligent Transportation Systems & Roadside Vision

Contact

jsham [at] etri.re.kr
218 Gajeong-ro, Yuseong-gu, Daejeon 34129, Republic of Korea

Education

PhD in EE, KAIST, 2023 ~ Present Advisor: Prof. Changick Kim
MS in Bio and Brain Engineering, KAIST, 2019 Advisor: Prof. Sung-Hong Park
BS in EE, Kyungpook National University, 2017

Research Experiences

Senior Researcher, Visual Intelligence Lab, ETRI, Mar 2019 ~ Present Intelligent transportation systems and pedestrian safety

Publications

TrajField: HD-Map-Free Roadside Trajectory Forecasting with Accumulated Traffic Fields

Je-Seok Ham, Seongwon Lee, Sungchan Oh, Jinyoung Moon, Changick Kim

ICRA 2027, under review

CIVITraj: A Practical Calibration-Free Framework and Dataset for Vehicle Trajectory Prediction from Urban Infrastructure

Je-Seok Ham, Hyunseo Lee, Yongseon Lee, Kwanyong Park, Jinyoung Moon, Changick Kim

IEEE Transactions on Intelligent Transportation Systems (T-ITS), under 1st review

Instruction-Tuned Multimodal Large Language Model for Generalizable Pedestrian Action Prediction in Urban Driving

Je-Seok Ham*, Jia Huang*, Peng Jiang, Jinyoung Moon, Srikanth Saripalli, Changick Kim

Engineering Applications of Artificial Intelligence (EAAI), 1st revision & under 2nd review

Infrastructure-Assisted Defensive Forecasting of Latent Traffic Hazards from Uncalibrated CCTV

Je-Seok Ham, Hyunseo Lee, Yongseon Lee, Kwanyong Park, Jinyoung Moon, Changick Kim

ECCV 2026 Workshops on Safe and Defensive Autonomous Driving

[ paper ]

Multimodal Understanding with GPT-4o to Enhance Generalizable Pedestrian Behavior Prediction

Je-Seok Ham, Jia Huang, Peng Jiang, Jinyoung Moon, Yongjin Kwon, Srikanth Saripalli, Changick Kim

Computers and Electrical Engineering, Vol. 129, No. 110741, 2026

Impact Factor: 5.5 · JCR: Top 15.80%

[ paper ]

WatchoutPed: A Dataset and Model for Vulnerable Pedestrian Anticipation in Surveillance Videos

Je-Seok Ham*, Dae Hoe Kim*, Jinyoung Moon

Knowledge-Based Systems, Vol. 316, No. 113352, 2025

Impact Factor: 7.6 · JCR: Top 12.50%

[ paper ]

Proactive Pedestrian Safety System by Fusing Trajectory Prediction with Semantic Ground Region Classification

Sungchan Oh*, Dae Hoe Kim*, Je-Seok Ham*, Jinyoung Moon

IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), 2025

[ paper ]

OmniPredict: GPT-4o Enhanced Multi-modal Pedestrian Crossing Intention Prediction

Je-Seok Ham, Jia Huang, Peng Jiang, Jinyoung Moon, Yongjin Kwon, Srikanth Saripalli, Changick Kim

NeurIPS 2024 Workshops on Adaptive Foundation Models

[ paper ]

LLaMAPed: Multi-modal Pedestrian Crossing Intention Prediction

Je-Seok Ham, Sunghun Kim, Jia Huang, Peng Jiang, Jinyoung Moon, Srikanth Saripalli, Changick Kim

ECCV 2024 Workshops, pp. 150–167

[ paper ]

CIPF: Crossing Intention Prediction Network based on Feature Fusion Modules for Improving Pedestrian Safety

Je-Seok Ham, Dae Hoe Kim, NamKyo Jung, Jinyoung Moon

CVPR 2023 Workshops, pp. 3665–3674 Citation: 86

[ paper ]

MCIP: Multi-Stream Network for Pedestrian Crossing Intention Prediction

Je-Seok Ham, Kangmin Bae, Jinyoung Moon

ECCV 2022 Workshops, pp. 663–679 Citation: 46

[ paper ]

Live Demonstration: A Neural Processor for AI Acceleration

Hyeji Kim, Jaehoon Chung, Kyoungseon Shin, Chun-Gi Lyuh, HyunMi Kim, Chan Kim, Yong Cheol Peter Cho, Jeongmin Yang, Je-Seok Ham, Minseok Choi, Jinho Han, Youngsu Kwon

IEEE International Symposium on Circuits and Systems (ISCAS), 2021

[ paper ]

HPC LINPACK Parameter Optimization on Homo-/Heterogeneous System of ARM Neoverse N1SDP

Je-Seok Ham, Yong Cheol Peter Cho, Ju-Yeob Kim, Chun-Gi Lyuh, Jin-Kyu Kim, Jinho Han, Youngsu Kwon

International Conference on High Performance Computing in Asia-Pacific Region (HPC Asia), 2021

[ paper ]

AB9: A Neural Processor for Inference Acceleration

Yong Cheol Peter Cho, Jaehoon Chung, Jeongmin Yang, Chun-Gi Lyuh, HyunMi Kim, Chan Kim, Je-Seok Ham, Minseok Choi, Kyoungseon Shin, Jinho Han, Youngsu Kwon

ETRI Journal, Vol. 42, No. 4, pp. 491–504, 2020 Citation: 14

Impact Factor: 1.094 · JCR: Top 80.263%

[ paper ]

Meningeal Lymphatic Vessels at the Skull Base Drain Cerebrospinal Fluid

Ji Hoon Ahn*, Hyunsoo Cho*, Jun-Hee Kim*, Shin Heun Kim, Je-Seok Ham, Intae Park, Sang Heon Suh, Seon Pyo Hong, Joo-Hye Song, Young-Kwon Hong, Yong Jeong, Sung-Hong Park, Gou Young Koh

Nature, Vol. 572, No. 7767, pp. 62–66, 2019 Citation: 959

Impact Factor: 43.07 · JCR: Top 0.725%

[ paper ]