Hank Chi-Hsi Kung
I am a research assistant at National Chiao Tung University in Taiwan, focusing on visual action representations learning and event identification under the supervision of Prof. Yi-Ting Chen and Dr. Yi-Hsuan Tsai.
This fall, I will be visiting Indiana University Bloomington to delve into the intersection of egocentric vision and cognitive science with Prof. David Crandall and Prof. Linda Smith.
Prior to this, I received my M.Sc from National Tsing-Hua University, where I was supervised by Prof. Che-Rung Lee, and B.Sc from National Taipei University.
I am actively looking for a Ph.D position starting from Fall 2025! I will join ECCV'24 in Milan in-person, please feel free to reach out!
Email /
Google Scholar /
Twitter /
Github
|
|
Research
I am interested in teaching machines to comprehend the world using structured representations rather than just "scaling". My research interest lies in the intersection of visual representation learning and robotics. Specifically, I aim to develop a compositional, indexable, and augmentable skill library for robot learning. Such extracted skills are reusable and can be composed for unseen tasks. My current research focuses on learning progress-aware action representations in long-form daily-life activities.
|
Publications
|
|
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
/
paper
/
arxiv
/
code
/
TACO dataset
We use Action-slot to represent atomic activities. The learned attention can discover and localize atomic activities with only weak video labels and without using any perception module (e.g., object detector).
|
|
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
/
paper
/
code
/
dataset
The FIRST benchmark that enables evaluation of various types of risk identification algorithms, namely, rule-based, trajectoy-prediction-based, collision prediction, and behavior-change-based. We also assess the influence of risk identification to the downstream driving task.
|
|
ADD: A Fine-grained Dynamic Inference Architecture for Semantic Image Segmentation
Chi-Hsi Kung and
Che-Rung Lee
IROS, 2021 & ACML 2021 MRVC workshop
paper
/
code
We use Neural Architecture Search (NAS) to find an optimal structure for dynamic inference on semantic segmentation.
|
Conference Reviewer
Advances in Neural Information Processing Systems (2024)
IEEE Conference on Computer Vision and Pattern Recognition (2023-2024)
IEEE International Conference on Development and Learning (2024)
|
Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.
|
|