Hyunjun Eun
AI Researcher, SK Telecom
Seoul, Republic of Korea
Email: hyunjun.eun@sk.com
Research Interests
My research interest lies in machine learning and computer vision for image and video understanding. Currently, I am working on large multimodal models (LMMs) to understand both general and document images. I am also exploring self-supervised vision models and vision-language models (VLMs) for large-scale visual encoders. Based on these researches, I have developed many service specific VLMs for image captioning, image retrieval, and tag recommendation.
In addition, I have conducted researches on temporal action detection for video understanding, text detection and recognition for optical character recognition.
Work Experience
AI Researcher at SK Telecom, Feb. 2020 - Current
Education
Ph.D. in Electrical Engineering, KAIST, South Korea, Sep. 2015 - Feb. 2020
M.S. in Electrical Engineering, KAIST, South Korea, Sep. 2013 - Aug. 2015
B.S. in Electrical Engineering, Kyungpook National University, South Korea, Mar. 2006 - Aug. 2013
Learning to Discriminate Information for Online Action Detection: Analysis and Application
Sumin Lee, Hyunjun Eun, Jinyoung Moon, Seokeon Choi, Yoonhyung Kim, Chanho Jung, Changick Kim
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 45, no. 5, pp. 5918-5934, May 2023.
[paper]
Temporal Filtering Networks for Online Action Detection
Hyunjun Eun, Jinyoung Moon, Jongyoul Park, Chanho Jung, Changick Kim
Pattern Recognition (PR), vol. 111, 107695, 2021.
[paper]
SRG: Snippet Relatedness-based Temporal Action Proposal Generator
Hyunjun Eun, Sumin Lee, Jinyoung Moon, Jongyoul Park, Chanho Jung, Changick Kim
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 30, no. 11, pp. 4232-4244, Nov. 2020.
[paper]
A Quad Edge-Based Grid Encoding Model for Content-Aware Image Retargeting
Yoonhyung Kim, Hyunjun Eun, Chanho Jung, Changick Kim
IEEE Transactions on Visualization and Computer Graphics (TVCG), vol. 25, no. 12, pp. 3202-3215, Dec. 2019.
[paper]
Single-View 2D CNNs with Fully Automatic Non-nodule Categorization for False Positive Reduction in Pulmonary Nodule Detection
Hyunjun Eun, Daeyeong Kim, Chanho Jung, Changick Kim
Computer Methods and Programs in Biomedicine (CMPB), vol.165, pp. 215-224, Oct. 2018.
[paper]
Saliency Refinement: Towards a Uniformly Highlighted Salient Object
Hyunjun Eun, Yoonhyung Kim, Chanho Jung, Changick Kim
Signal Processing: Image Communication (SPIC), vol. 62, pp. 16-32, Mar. 2018.
[paper]
Superpixel-Guided Adaptive Image Smoothing
Hyunjun Eun, Changick Kim
IEEE Signal Processing Letters (SPL), vol. 23, no. 12, pp. 1887-1891, Dec. 2016.
[paper]
Honors and Awards
First Place, Advanced League, SK AI Challenge in ICHEON Forum 2021
For defect detection in SKC films, we achieved 0.6925 mAP on 11 defect classes.
Best Dissertation Award in 2020, Electrical Engineering, KAIST
Dissertation: Temporal Convolutional Networks for Offline and Online Action Detection
Paper Competition Award, Qualcomm-KAIST Innovation Awards 2019
Paper: SRG: Snippet Relatedness-based Temporal Action Proposal Generator
LG Electronics Paper Award, IEIE Autumn Annual Conference 2018
Paper: Weakly Supervised Clothes Recognition with a Two-Branch Network
First Place, Samsung Fire & Marine Insurance (SFMI) Machine Learning Challenge 2017
For Korean text detection in traffic road signs, we achieved 98.14% accuracy on 709 Korean text classes.
Talks
Multimodal AI: Understanding and Generation, Sep. 2023.
SKT AI Curriculum-Seoul National University
Vision-Language Pre-training, Nov. 2022.
Chungnam National University
Generalized OCR, Nov. 2021.
SK ICT Tech Summit 2021
Generalized OCR, Oct. 2021
SKT NUGU Conference 2021
Services
Reviewer for
IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
IEEE Transactions on Multimedia (TMM)
IEEE Signal Processing Letters (SPL)
Medical Physics
Academic Experiences
Teaching Assistant for
Optimization in Computer Vision, 2019, KAIST
EE734 Image Understanding, Spring 2019, KAIST
Optimization in Computer Vision, 2018, KAIST
EE734 Image Understanding, Spring 2018, KAIST
EE305A Electronics Design Lab., Fall 2016, KAIST
EE734 Image Understanding, Spring 2016, KAIST
Exchange Student
Spring 2012, Wroclaw University of Science and Technology
Pre-Internship
Biomedical Engineering, Winter 2011, The University of Sydney