In-Jae Yu

In-Jae Yu

Auto-generated profile, based on publicly available information

In-Jae Yu

School of Computing, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, South Korea

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
25 May 2022 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
MKMyung-Joon Kwon
Myung-Joon Kwon
SNSeung-Hun Nam
Seung-Hun Nam
IYIn-Jae Yu
In-Jae Yu
HLHeung-Kyu Lee
Heung-Kyu Lee
CKChangick Kim
Changick Kim

1 August 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
SNSeung-Hun Nam
Seung-Hun Nam
WAWonhyuk Ahn
Wonhyuk Ahn
IYIn-Jae Yu
In-Jae Yu
MKMyung-Joon Kwon
Myung-Joon Kwon
MSMinseok Son
Minseok Son
HLHeung-Kyu Lee
Heung-Kyu Lee
Seam carving is a representative content-aware image retargeting approach to adjust the size of an image. To preserve visually prominent content, seam-carving algorithms first calculate the connected path of pixels, referred to as the seam, according to a defined cost function and then adjust the size of an image by removing or duplicating repeatedly calculated seams. Seam carving is actively exploited to overcome diversity in the resolution of images between applications and devices; hence, detecting the distortion caused by seam carving has become important in image forensics. In this paper, we propose a convolutional neural network (CNN)-based approach to classifying seam-carving forgery. To attain the ability to learn low-level features, we designed a convolutional neural network (CNN) architecture comprising five types of network blocks specialized in capturing local artifacts caused by seam carving. An ensemble module is further adopted to both enhance performance and comprehensively analyze the features in the local areas. To validate the effectiveness of our work, extensive experiments based on various CNN-based baselines were conducted. Compared to the baselines, our work exhibits state-of-the-art performance in terms of three-class classification (original, seam inserted, and seam removed). The experimental results also demonstrate that our model with the ensemble module is robust for various unseen cases.

24 July 2019 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
YLYongsub Lim
Yongsub Lim
IYInjae Yu
Injae Yu
DSDongmin Seo
Dongmin Seo
UKU Kang
U Kang
LSLee Sael
Lee Sael
How can we obtain fast and high-quality clusters in genome scale bio-networks? Graph clustering is a powerful tool applied on bio-networks to solve various biological problems such as protein complexes detection, disease module detection, and gene function prediction. Especially, MCL (Markov Clustering) has been spotlighted due to its superior performance on bio-networks. MCL, however, is skewed towards finding a large number of very small clusters (size 1-3) and fails to detect many larger clusters (size 10+). To resolve this fragmentation problem, MLR-MCL (Multi-level Regularized MCL) has been developed. MLR-MCL still suffers from the fragmentation and, in cases, unrealistically large clusters are generated. In this paper, we propose PS-MCL (Parallel Shotgun Coarsened MCL), a parallel graph clustering method outperforming MLR-MCL in terms of running time and cluster quality. PS-MCL adopts an efficient coarsening scheme, called SC (Shotgun Coarsening), to improve graph coarsening in MLR-MCL. SC allows merging multiple nodes at a time, which leads to improvement in quality, time and space usage. Also, PS-MCL parallelizes main operations used in MLR-MCL which includes matrix multiplication. Experiments show that PS-MCL dramatically alleviates the fragmentation problem, and outperforms MLR-MCL in quality and running time. We also show that the running time of PS-MCL is effectively reduced with parallelization.

1 September 2017
Verified
Conference Paper
Closed access
IYIn-Jae Yu
In-Jae Yu
DKDo-Guk Kim
Do-Guk Kim
JPJin-Seok Park
Jin-Seok Park
Jong-Uk HouJong-Uk Hou
Jong-Uk Hou
SCSunghee Choi
Sunghee Choi
HLHeung-Kyu Lee
Heung-Kyu Lee
As computer graphics technology advances, it is becoming increasingly difficult to determine whether a given picture was taken by camera or via computer graphics. In this work, we propose a method to using simple CNN structures to identify photorealistic computer graphics (PRCG) using convolutional neural networks (CNN). This network trained to identify the source of image patches. We showed the network without pooling layer showed 98.2% accuracy, which is 2.1% higher than the result of using conventional object-recognition network. Testing random patches from image, the accuracy of identifying image reached 98.5%. Furthermore, it is possible to detect the photograph-PRCG synthesized regions from the image.

1 September 2019
Verified
Conference Paper
Closed access
SNSeung-Hun Nam
Seung-Hun Nam
JPJinseok Park
Jinseok Park
DKDongkyu Kim
Dongkyu Kim
IYIn-Jae Yu
In-Jae Yu
TKTae-Yeon Kim
Tae-Yeon Kim
HLHeung-Kyu Lee
Heung-Kyu Lee
Double compression (DC) involves compressing a video twice with the video codec. DC usually occurs when a compressed video is manipulated, because most videos are saved in the compression format after manipulating. Given this principle, if we can detect DC traces in videos, we can determine whether a video has been manipulated. Prior works have proposed methods for detecting DC of H.264 videos; however, they have limitations in that they can detect DC only for a limited dataset and set of compression parameters. To overcome these limitations, we propose a two-stream neural network that incorporates two components that analyze intra-coded frames and predictive frames. We explain why the proposed two-stream neural network can detect DC traces in videos more accurately than the prior method, and we demonstrate that the proposed network can detect DC videos that have various contents and parameters through extensive experiments.

1 September 2019
Verified
Conference Paper
Closed access
SNSeung-Hun Nam
Seung-Hun Nam
WAWonhyuk Ahn
Wonhyuk Ahn
SMSeung-Min Mun
Seung-Min Mun
JPJinseok Park
Jinseok Park
DKDongkyu Kim
Dongkyu Kim
HLHeung-Kyu Lee
Heung-Kyu Lee
Content-aware image resizing is the process of adjusting the size of an image while preserving its important content. Image resizing is used to overcome diversity in resolutions between modules, such as display devices and applications, and can thus be deliberately exploited to distort or remove original content; therefore, detecting such tampering has become an important topic in forensics. This paper proposes a deep neural network architecture to capture subtle local artifacts caused by seam-based image resizing. Unlike past approaches that only classified two classes, our approach is the first attempt to solve a given forensic task with three-class classification: original, seam insertion, and seam carving. The experimental results show that our work performs better than the handcrafted feature-based method and networks designed for different forensic tasks.