Hank Chi-Hsi Kung 孔啟熙

I am a PhD student at Northeastern University, where I am working with Prof. Lorenzo Torresani. Previously, I was a visiting researcher at Indiana University, working with Prof. David Crandall and Prof. Linda Smith. Before that, I was a research assistant at National Yang Ming Chiao Tung University, supervised by Prof. Yi-Ting Chen and Dr. Yi-Hsuan Tsai.

Selected Publications

Overview of active multiview learning through self-generated visual experience

Self-generated visual experience shapes generalization in active multiview learning

Chi-Hsi Kung, Frangil Ramirez, Yi-Ting Chen, David Crandall, Linda Smith

Paper coming soon Code coming soon

Preview of state-change counterfactuals for procedure-aware video representation learning

What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning

Chi-Hsi Kung*, Frangil Ramirez*, Juhyung Ha, Yi-Ting Chen, David Crandall, Yi-Hsuan Tsai (* Equal Contribution)

ICCV 2025, CVPR EgoVIS 2025

ICCV arXiv Code

Action-slot visualizations of atomic activities in traffic scenes

Action-slot: Visual Action-centric Representations for Atomic Activity Recognition in Traffic Scenes

Chi-Hsi Kung, Shu-Wei Lu, Yi-Hsuan Tsai, Yi-Ting Chen

CVPR, 2024

Project page CVPR arXiv Code TACO dataset

RiskBench traffic scenarios for identifying driving risks

RiskBench: A Scenario-based Benchmark for Risk Identification

Chi-Hsi Kung, Chieh-Chi Yang, Pang-Yuan Pao, Shu-Wei Lu, Pin-Lun Chen, Hsin-Cheng Lu, Yi-Ting Chen

ICRA, 2024

Project page Video ICRA Code Dataset

Award

Khoury Distinguished Scholar to the Doctor of Philosophy (PhD) in Computer Science

Conference Reviewer

IEEE Conference on Computer Vision and Pattern Recognition CVPR 2023–2025
The International Conference on Machine Learning ICML 2025
International Conference on Computer Vision ICCV 2025
Advances in Neural Information Processing Systems NeurIPS 2024
IEEE International Conference on Development and Learning ICDL 2024
IEEE/RSJ International Conference on Intelligent Robots and Systems IROS 2025