Hyunjun Eun

Ph. D. Student
Computational Intelligence Lab.
School of Electrical Engineering, KAIST

Research

My research focuses on temporal detection of actions, activities, and events in videos. Previously, I have also researched on detection of objects in several types of images (texts, salient objects, lung nodules, and dental caries).


News

- Our team won the first place in Korean Text Detection in Traffic Road Signs of Samsung Fire & Marine Insurance Machine Learning Challenge 2017. We achieved 98.14% accuracy with 0.17 fps on 709 Korean text classes.


Representative Publications

Single-View 2D CNNs with Fully Automatic Non-nodule Categorization for False Positive Reduction in Pulmonary Nodule Detection
Hyunjun Eun, Daeyeong Kim, Chanho Jung, and Changick Kim.
Computer Methods and Programs in Biomedicine (CMPB), 2018.

Saliency Refinement: Towards a Uniformly Highlighted Salient Object
Hyunjun Eun, Yoonhyung Kim, Chanho Jung, and Changick Kim.
Signal Processing: Image Communication (SPIC), 2018.

Fast Korean Text Detection and Recognition in Traffic Guide Signs
Hyunjun Eun, Jonghee Kim, Jinsu Kim, and Changick Kim.
IEEE International Conference on Visual Communications and Image Processing (VCIP), 2018.

Superpixel-Guided Adaptive Image Smoothing
Hyunjun Eun and Changick Kim.
IEEE Signal Processing Letters (SPL), 2016.


Publications

Landmark-free Clothes Recognition with a Two-Branch Feature Selective Network
Sumin Lee, Hyunjun Eun, Sungchan Oh, Wonjun Kim, Chanho Jung, and Changick Kim.
Electronics Letters, accepted.

A Quad Edge-Based Grid Encoding Model for Content-Aware Image Retargeting
Yoonhyung Kim, Hyunjun Eun, Chanho Jung, and Changick Kim.
IEEE Transactions on Visualization and Computer Graphics (TVC), accepted.

Boosting Proximal Dental Caries Detection via Combination of Variational Methods and Convolutional Neural Network
Joonhyang Choi, Hyunjun Eun, and Changick Kim.
Journal of Signal Processing Systems (JSPS), 2018.

Oriented Tooth Localization for Periapical Dental X-ray Images via Convolutional Neural Network
Hyunjun Eun and Changick Kim.
IEEE Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2016.

Salient Object Detection Using HOS Based L0 Smoothing and Shape-Aware Region Merging
Hyunjun Eun, Jonghee Kim, and Changick Kim.
IEEE International Conference on Visual Communications and Image Processing (VCIP), 2015.

No-reference Image Quality Assessment Based on Singular Value Decomposition without Learning
Jonghee Kim, Hyunjun Eun, and Changick Kim.
Pacific-rim Conference on Multimedia (PCM), 2015.

단순선형반복군집을 위한 적응적 초기 군집 중심 샘플링 방법
Hyunjun Eun, 김윤형, 정찬호, 김창익.
한국통신학회논문지, 2018.

조건부 무작위장을 사용한 세그넷의 시맨틱 영상 분할 성능 향상
김윤형, Hyunjun Eun, 정찬호, 김창익.
한국통신학회논문지, 2018.

두 개 분기 네트워크를 이용한 약지도 의류 인식
이수민, Hyunjun Eun, 정찬호, 오성찬, 김창익.
대한전자공학회 추계학술대회, 2018.

농구 전광판 동영상에서의 의사결정 트리 기반 숫자 인식
Hyunjun Eun, 이지원, 문성원, 이정수, 남도원, 정찬호, 김창익.
한국통신학회논문지, 2017.

저해상도 농구 전광판 동영상에서의 문맥 기반 선수 득점 인식
Hyunjun Eun, 이지원, 문성원, 이정수, 남도원, 정찬호, 김창익.
한국통신학회논문지, 2017.

CNN을 이용한 인접면 치아 우식 검출
최준향, Hyunjun Eun, 김창익.
대한전자공학회 추계학술대회, 2015.

패치 분류를 이용한 자동 시드 추출 및 객체 분할
Hyunjun Eun, 최지원, 김창익.
대한전자공학회 하계종합학술대회, 2014.


Contact

Email: hj.eun[at]kaist.ac.kr