Hunjoo Lee

Hunjoo Lee

Auto-generated profile, based on publicly available information

Hunjoo Lee

Intelligent Convergence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon 34129, Korea

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 January 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SKSeonjae Kim
Seonjae Kim
Dongsan JunDongsan Jun
Dongsan Jun
Byung-Gyu  KimByung-Gyu Kim
Byung-Gyu Kim
HLHunjoo Lee
Hunjoo Lee
EREunjun Rhee
Eunjun Rhee
There are many studies that seek to enhance a low resolution image to a high resolution image in the area of super-resolution. As deep learning technologies have recently shown impressive results on the image interpolation and restoration field, recent studies are focusing on convolutional neural network (CNN)-based super-resolution schemes to surpass the conventional pixel-wise interpolation methods. In this paper, we propose two lightweight neural networks with a hybrid residual and dense connection structure to improve the super-resolution performance. In order to design the proposed networks, we extracted training images from the DIVerse 2K (DIV2K) image dataset and investigated the trade-off between the quality enhancement performance and network complexity under the proposed methods. The experimental results show that the proposed methods can significantly reduce both the inference speed and the memory required to store parameters and intermediate feature maps, while maintaining similar image quality compared to the previous methods.

4 December 2013 in ETRI Journal
Verified
Journal Article
Open access
PDF file
YCYeounoh Chung
Yeounoh Chung
CPChang‐Yong Park
Chang‐Yong Park
NKNoo-ri Kim
Noo-ri Kim
HCHana Cho
Hana Cho
TYTaebok Yoon
Taebok Yoon
JLJee-Hyong Lee
Jee-Hyong Lee
An approach for game bot detection in massively multiplayer online role‐playing games (MMORPGs) based on the analysis of game playing behavior is proposed. Since MMORPGs are large‐scale games, users can play in various ways. This variety in playing behavior makes it hard to detect game bots based on play behaviors. To cope with this problem, the proposed approach observes game playing behaviors of users and groups them by their behavioral similarities. Then, it develops a local bot detection model for each player group. Since the locally optimized models can more accurately detect game bots within each player group, the combination of those models brings about overall improvement. Behavioral features are selected and developed to accurately detect game bots with the low resolution data, considering common aspects of MMORPG playing. Through the experiment with the real data from a game currently in service, it is shown that the proposed local model approach yields more accurate results.

4 December 2013 in ETRI Journal
Verified
Journal Article
Open access
PDF file
KKKyoung Ill Kim
Kyoung Ill Kim
SBSu Young Bae
Su Young Bae
DLDong Chun Lee
Dong Chun Lee
CCChang Sik Cho
Chang Sik Cho
HLHun Joo Lee
Hun Joo Lee
ALAnd Kyuchul Lee
And Kyuchul Lee
To implement a cloud game service platform supporting multiple users and devices based on real‐time streaming, there are many technical needs, including game screen and sound capturing, audio/video encoding in real time created by a high‐performance server‐generated game screen, and real‐time streaming to client devices, such as low‐cost PCs, smart devices, and set‐top boxes. We therefore present a game service platform for the running and management of the game screen, as well as running the sound on the server, in which the captured and encoded game screen and sound separately provide client devices through real‐time streaming. The proposed platform offers Web‐based services that allow game play on smaller end devices without requiring the games to be installed locally.

12 May 2021 in Sensors
Verified
Journal Article
Open access
PDF file
LYLee Yooho
Lee Yooho
Dongsan JunDongsan Jun
Dongsan Jun
Byung-Gyu  KimByung-Gyu Kim
Byung-Gyu Kim
HLHunjoo Lee
Hunjoo Lee
Super resolution (SR) enables to generate a high-resolution (HR) image from one or more low-resolution (LR) images. Since a variety of CNN models have been recently studied in the areas of computer vision, these approaches have been combined with SR in order to provide higher image restoration. In this paper, we propose a lightweight CNN-based SR method, named multi-scale channel dense network (MCDN). In order to design the proposed network, we extracted the training images from the DIVerse 2K (DIV2K) dataset and investigated the trade-off between the SR accuracy and the network complexity. The experimental results show that the proposed method can significantly reduce the network complexity, such as the number of network parameters and total memory capacity, while maintaining slightly better or similar perceptual quality compared to the previous methods.

26 October 2015 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
YCYeonJun Choi
YeonJun Choi
SCSungJune Chang
SungJune Chang
YKYongJun Kim
YongJun Kim
HLHunJoo Lee
HunJoo Lee
WSWookHo Son
WookHo Son
SJSeongIl Jin
SeongIl Jin

15 January 2014 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
SSSangHyun Seo
SangHyun Seo
HLHunJoo Lee
HunJoo Lee