My primary research areas are computer vision and deep learning, with specific interests in streaming video understanding, perception for action, vision for robotics, and representation learning.
CV / LinkedIn / GitHub/Research Statement
Contact: yume.mizuki.yume <|at|> gmail.com
Senior Engineer @ Qualcomm
Education
Ph.D. in Computer Science, Yonsei University, Seoul, Korea [Mar 2020 - Aug 2025] Advisor: Seon Joo Kim
Dissertation: Online Temporal Understanding Methods for Streaming Videos [link]
B.S. in Computer Science, Yonsei University, Seoul, Korea [Mar 2014 - Feb 2020]
GPA 3.85/4.3 -- Top 8% in Dept. of Computer Science
Research Experience
École nationale des ponts et chaussées (Visiting Ph.D student) [Oct 2024 - Feb 2025]
Qualcomm (Research Intern) [Mar 2025 - Aug 2025]
Qualcomm (Senior Engineer) [Sep 2025 - Current]
Research Objective
My main research direction revolves around the challenge of efficient streaming perception in embodied AI and robotics. This area is vital because, unlike traditional models, embodied agents often lack complete observational data, necessitating real-time, sequential decision-making based on partial, streaming inputs. This mirrors how humans process visual information continuously, not in isolated instances.
Moving forward from my previous research, I am now focusing on integrating video perception models with Vision-Language Models (VLMs) and extending their applications to robotics, actively collaborating with Professor Youngwoon Lee.
You can assess my full research statement here.
Hanjung Kim*, Jaehyun Kang*, Hyolim Kang, Meedeum Cho, Seon Joo Kim, Youngwoon Lee
CoRL 2025
Hyolim Kang*, Yunsu Park*, Youngbeom Yoo, Yeeun Choi, Seon Joo Kim
ICCV 2025
Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization
Jeongseok Hyun, Su Ho Han, Hyolim Kang, Joon-Young Lee, Seon Joo Kim
WACV 2025
ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos
Hyolim Kang, Jeongseok Hyun, Joungbin An, Youngjae Yu, Seon Joo Kim
ECCV 2024
Object Aware Egocentric Online Action Detection
Joungbin An, Yunsu Park, Hyolim Kang, Seon Joo Kim
CVPR 2024 First Joint Egocentric Vision Workshop
MiniROAD: Minimal RNN Framework for Online Action Detection
Joungbin An, Hyolim Kang, Su Ho Han, Ming-Hsuan Yang, Seon Joo Kim
ICCV 2023
Project Page / Paper / Code
Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks
Hyolim Kang, Hanjung Kim, Joungbin An, Minsu Cho, Seon Joo Kim
CVPR 2023
ComMU: Dataset for Combinatorial Music Generation
Lee Hyun*, Taehyun Kim*, Hyolim Kang, Minjoo Ki, Hyeonchan Hwang, Kwanho Park, Sharang Han, Seon Joo Kim
Neurips 2022 Datasets & Benchmarks
A Sliding Window Scheme for Online Temporal Action Localization
Young Hwi Kim, Hyolim Kang, Seon Joo Kim,
ECCV 2022
UBoCo : Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection
Hyolin Kang*, Jinwoo Kim*, Taehyun Kim, Seon Joo Kim
CVPR 2022
CAG-QIL: Context-Aware Actionness Grouping via Q Imitation Learning
for Online Temporal Action Localization
Hyolin Kang, Kyungmin Kim, Yumin Ko, Seon Joo Kim
ICCV 2021
Selected as the best vision paper in the 2022 Yonsei AI Workshop
($2000 worth of prize)
Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach
Hyolin Kang, Jinwoo Kim, Kyungmin Kim, Taehyun Kim, Seon Joo Kim
CVPR 2021 LOng-form VidEo Understanding (LOVEU) Workshop
1st place in both track1.1 & track1.2
I'm also an amateur composer and piano player. If you are interested, here are some of my original pieces & playing!
Original Compositions (including a little fugue)
Playing Bach & Chopin