Sangjin Lee

Dr. Sangjin Lee

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
24 October 2022
Verified
Book Chapter
Closed access
PDF file
CSChajin Shin
Chajin Shin
HLHyeongmin Lee
Hyeongmin Lee
HSHanbin Son
Hanbin Son
SLSangjin Lee
Sangjin Lee
DLDogyoon Lee
Dogyoon Lee
SLSangyoun Lee
Sangyoun Lee

24 June 2021 in IEEE Access
Verified
Journal Article
Open access
TKTaeoh Kim
Taeoh Kim
CSChajin Shin
Chajin Shin
SLSangjin Lee
Sangjin Lee
SLSangyoun Lee
Sangyoun Lee
Image restoration based on the Deep Convolutional Neural Network (CNN) based image restoration has demonstrated promising results in many sub-tasks, such as image super-resolution, compression artifacts removal, image denoising, and image enhancement. Compared to many CNN-based high-level vision tasks that predict sparse probabilities of each class, the CNN for image restoration requires dense pixel-level predictions with precise intensity-level values. Therefore, a minimum number of spatial pooling (or down-sampling) operations is required to maintain the image details. Therefore, designing a fast or lightweight model for image restoration is a difficult problem and is even more critical when the spatial resolution of an image becomes larger. In this paper, we propose a family of networks called Subpixel Prediction Networks (SPNs) that predict reshaped and spatially down-sampled block-wise tensors instead of raw images with full resolution. Under this scheme, spatial downsampling decreases the restoration performance less while making the network faster. We propose a novel Subpixel Block Attention (SBA) module that re-calibrates blockwise features to diminish blockwise discontinuity to increase the performance further. The experimental results reveal that these networks demonstrate good trade-offs between speed (number of computations) and restoration performance in the three image restoration tasks: image compression artifacts removal, color image denoising, and image enhancement.

31 December 2018 in Korean Journal of Sports Science
Verified
Journal Article
Closed access
SLSangjin Lee
Sangjin Lee
BLBeon Lee
Beon Lee
The purpose of this study is to provide basic data for improving school safety education by analyzing the effect of school safety education on safety behavior of high school students. The subjects of this study were eight classes of U high school in Uiwang-si, Gyeonggi-do. They were educated for five minutes on the seven standards for safety education at the beginning of the physical education class for four months. A questionnaire was used as a research tool. Before and after the study, the researcher distributed questionnaires, and the statistics used 270 copies of the questionnaire collected after the study subjects responded by using self-assessment methods. The conclusions obtained by using the SPSS Win 21.0 and AMOS 19.0 programs for frequency analysis, percent calculation, Cronbach`s a coefficient, confirmed factor analysis, and response sample t-test are as follows: First, in the active participation of safety education, experimental group showed more active participation in safety education than control group at p>.05 level between experimental group and control group. Also, pre-post test of experimental group showed significant improvement at p>.05 level. Second, in active behavior according to education, the experimental group showed more active behavior than the control group at the p>.05 level between the experimental group and the control group. Also, pre-post test of experimental group showed significant improvement at p>.05 level. Third, in enhancing friend safety, the experimental group showed more actively help the peer safety than the control group at the p>.05 level between the experimental group and the control group. Also, pre-post test of experimental group showed significant improvement at p>.05 level. Fourth, in the positive compliance with safety regulations, the experimental group showed a positive compliance with the safety rules compared to the control group at the p>.05 level between the experimental group and the control group. Also, pre-post test of experimental group showed significant improvement at p>.05 level. In this conclusion, more active and systematic safety education, which entails action, should be conducted in schools.

6 January 2025 in Sensors
Verified
Journal Article
Open access
PDF file
SLSangjin Lee
Sangjin Lee
CSChajin Shin
Chajin Shin
HKHong-Goo Kang
Hong-Goo Kang
SLSangyoun Lee
Sangyoun Lee
Video frame interpolation (VFI) is a task that generates intermediate frames from two consecutive frames. Previous studies have employed two main approaches to extract the necessary information from both frames: pixel-level synthesis and flow-based methods. However, when synthesizing high-resolution videos using VFI, each approach has its limitations. Pixel-level synthesis based on the transformer architecture requires high complexity to achieve 4K video results. In the case of flow-based methods, forward warping can produce holes where pixels are not allocated, while backward warping approaches struggle to obtain accurate backward flow. Additionally, there are challenges during the training stage; previous works have often generated suboptimal results by training multi-stage model architectures separately. To address these issues, we propose a Recurrent Flow Update (RFU) model trained in an end-to-end manner. We introduce a global flow update module that leverages global information to mitigate the weaknesses of forward flow and gradually correct errors. We demonstrate the effectiveness of our method through several ablation studies. Our approach achieves state-of-the-art performance not only on the XTest and Davis datasets, which have 4K resolution, but also on the SNU-FILM dataset, which features large motions at low resolution.

27 May 2020 in arXiv
Verified
Preprint
Open access
PDF file
SLSangjin Lee
Sangjin Lee
HLHyeongmin Lee
Hyeongmin Lee
TKTaeoh Kim
Taeoh Kim
SLSangyoun Lee
Sangyoun Lee
Video frame extrapolation is a task to predict future frames when the past frames are given. Unlike previous studies that usually have been focused on the design of modules or construction of networks, we propose a novel Extrapolative-Interpolative Cycle (EIC) loss using pre-trained frame interpolation module to improve extrapolation performance. Cycle-consistency loss has been used for stable prediction between two function spaces in many visual tasks. We formulate this cycle-consistency using two mapping functions; frame extrapolation and interpolation. Since it is easier to predict intermediate frames than to predict future frames in terms of the object occlusion and motion uncertainty, interpolation module can give guidance signal effectively for training the extrapolation function. EIC loss can be applied to any existing extrapolation algorithms and guarantee consistent prediction in the short future as well as long future frames. Experimental results show that simply adding EIC loss to the existing baseline increases extrapolation performance on both UCF101 and KITTI datasets.

1 January 2026 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
SLSangjin Lee
Sangjin Lee
CSChajin Shin
Chajin Shin
HKHong-Goo Kang
Hong-Goo Kang
SLSangyoun Lee
Sangyoun Lee
With recent increases in the demand for high-resolution video content, it has become increasingly challenging to transmit video data within the constraints of limited band-width. Due to the time-consuming nature of developing and disseminating new standard codecs, a large body of research has addressed improving low-quality videos through post-processing techniques. Previous studies have primarily concentrated on enhancing the quality of compressed video by addressing the temporal consistency of adjacent frames over short durations. However, these approaches often overlook specific characteristics of the video coding framework, such as notable variations in codec artifact patterns occurring at the Group of Pictures (GoP) level, which can result in considerable viewer discomfort. In this paper, we propose GoP-based Quality Enhancement (GQE), which aims to improve the quality of compressed videos by addressing issues at the GoP level. First, we present a GoP Guided Feature Propagation (GGFP) module, which addresses the root cause of the GoP level issue by propagating features from the I-frame of a different GoP to the frames currently undergoing enhancement. Then, we introduce a Temporal Aggregation (TA) module to efficiently and effectively aggregate features from the I-frame and the current frame. We extensively evaluate our model using diverse test sequences across a range of codecs, including HEVC, VP9, and AV1. Our approach not only achieves a significant reduction in the pattern shifts of GoP-level artifacts, but also demonstrates a substantial improvement in overall video quality.