Je Woo Kim

Mr. Je Woo Kim


Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
2 May 2019 in Symmetry
Verified
Journal Article
Open access
PDF file
HAHa-eun Ahn
Ha-eun Ahn
JJJinwoo Jeong
Jinwoo Jeong
JKJe Woo Kim
Je Woo Kim
Visual quality and algorithm efficiency are two main interests in video frame interpolation. We propose a hybrid task-based convolutional neural network for fast and accurate frame interpolation of 4K videos. The proposed method synthesizes low-resolution frames, then reconstructs high-resolution frames in a coarse-to-fine fashion. We also propose edge loss, to preserve high-frequency information and make the synthesized frames look sharper. Experimental results show that the proposed method achieves state-of-the-art performance and performs 2.69x faster than the existing methods that are operable for 4K videos, while maintaining comparable visual and quantitative quality.

7 October 2019 in Symmetry
Verified
Journal Article
Open access
PDF file
HAHa-eun Ahn
Ha-eun Ahn
JJJinwoo Jeong
Jinwoo Jeong
JKJe Woo Kim
Je Woo Kim
Soonchul KwonSoonchul Kwon
Soonchul Kwon
HJHyunjo Jung
Hyunjo Jung
Recently, video frame interpolation research developed with a convolutional neural network has shown remarkable results. However, these methods demand huge amounts of memory and run time for high-resolution videos, and are unable to process a 4K frame in a single pass. In this paper, we propose a fast 4K video frame interpolation method, based upon a multi-scale optical flow reconstruction scheme. The proposed method predicts low resolution bi-directional optical flow, and reconstructs it into high resolution. We also proposed consistency and multi-scale smoothness loss to enhance the quality of the predicted optical flow. Furthermore, we use adversarial loss to make the interpolated frame more seamless and natural. We demonstrated that the proposed method outperforms the existing state-of-the-art methods in quantitative evaluation, while it runs up to 4.39× faster than those methods for 4K videos.

1 August 2015 in ETRI Journal
Verified
Journal Article
Open access
PDF file
CCChoongsang Cho
Choongsang Cho
JKJe Woo Kim
Je Woo Kim
SLSangkeun Lee
Sangkeun Lee
This paper describes an audio source separation that is based on nonnegative matrix factorization (NMF) and expectation maximization (EM). For stable and high-performance separation, an effective auxiliary source separation that extracts source residuals and reprojects them onto proper sources is proposed by taking into account an ambiguous region among sources and a source's refinement. Specifically, an additional NMF (model) is designed for the ambiguous region — whose elements are not easily represented by any existing or predefined NMFs of the sources. The residual signal can be extracted by inserting the aforementioned model into the NMF-EM-based audio separation. Then, it is refined by the weighted parameters of the separation and reprojected onto the separated sources. Experimental results demonstrate that the proposed scheme (outlined above) is more stable and outperforms existing algorithms by, on average, 4.4 dB in terms of the source distortion ratio.

22 December 2022 in Symmetry
Verified
Journal Article
Open access
PDF file
ICInho Chang
Inho Chang
MPMin-Gyu Park
Min-Gyu Park
JKJe Woo Kim
Je Woo Kim
JYJu Hong Yoon
Ju Hong Yoon
We present a simple yet effective pipeline for absolute three-dimensional (3D) human pose estimation from two-dimensional (2D) joint keypoints, namely, the 2D-to-3D human pose lifting problem. Our method comprises two simple baseline networks, a 3D conversion function, and a correction network. The former two networks predict the root distance and the root-relative joint distance simultaneously. Given the input and predicted distances, the 3D conversion function recovers the absolute 3D pose, and the correction network reduces 3D pose noise caused by input uncertainties. Furthermore, to cope with input noise implicitly, we adopt a Siamese architecture that enforces the consistency of features between two training inputs, i.e., ground truth 2D joint keypoints and detected 2D joint keypoints. Finally, we experimentally validate the advantages of the proposed method and demonstrate its competitive performance over state-of-the-art absolute 2D-to-3D pose-lifting methods.

30 March 2012 in Journal of Broadcast Engineering
Verified
Journal Article
Closed access
YHYoung-Bae Hwang
Young-Bae Hwang
JKJe Woo Kim
Je Woo Kim
BCByeong-Ho Choi
Byeong-Ho Choi

1 October 2026
Verified
Book Chapter
Closed access
PDF file
YHYuqi Hou
Yuqi Hou
ZCZhuo Chen
Zhuo Chen
Han HuHan Hu
Han Hu
JKJe Woo Kim
Je Woo Kim
JJJianbo Jiao
Jianbo Jiao
HCHyung Jin Chang
Hyung Jin Chang