Sangyun Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Sangyun Lee has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Doyeop Lee
Department of Architectural Engineering, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul 06974, Republic of Korea
1 shared publication - Euntai Kim
Yonsei University
1 shared publication - Kwangjin Yoon
SI Analytics
1 shared publication Seok Ryu
1 shared publication- Seokjun Song1 shared publication
Sewoong Ahn
SI Analytics
1 shared publication
Latest Publications
- 5 December 2025
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 23 (12) , 3702-3713
StoneGAT: A Robust Fall Detection Framework via Skeleton-aware Graph Attention Networks
- 5 December 2025
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 23 (12) , 3702-3713
StoneGAT: A Robust Fall Detection Framework via Skeleton-aware Graph Attention Networks
- Open Access
- 13 December 2023
- Published by Elsevier in ICT Express
- Vol. 10 (3) , 570-575
Making TSM better: Preserving foundational philosophy for efficient action recognition
- 13 December 2023
- Published by Elsevier in ICT Express
- Vol. 10 (3) , 570-575
Open AccessMaking TSM better: Preserving foundational philosophy for efficient action recognition
- Open Access
Learning Multiple Probabilistic Degradation Generators for Unsupervised Real World Image Super Resolution
Unsupervised real world super resolution (USR) aims to restore high-resolution (HR) images given low-resolution (LR) inputs, and its difficulty stems from the absence of paired dataset. One of the most common approaches is synthesizing noisy LR images using GANs (i.e., degradation generators) and utilizing a synthetic dataset to train the model in a supervised manner. Although the goal of training the degradation generator is to approximate the distribution of LR images given a HR image, previous works have heavily relied on the unrealistic assumption that the conditional distribution is a delta function and learned the deterministic mapping from the HR image to a LR image. In this paper, we show that we can improve the performance of USR models by relaxing the assumption and propose to train the probabilistic degradation generator. Our probabilistic degradation generator can be viewed as a deep hierarchical latent variable model and is more suitable for modeling the complex conditional distribution. We also reveal the notable connection with the noise injection of StyleGAN. Furthermore, we train multiple degradation generators to improve the mode coverage and apply collaborative learning for ease of training. We outperform several baselines on benchmark datasets in terms of PSNR and SSIM and demonstrate the robustness of our method on unseen data distribution. Code is available at https://github.com/sangyun884/MSSR.
Open AccessLearning Multiple Probabilistic Degradation Generators for Unsupervised Real World Image Super Resolution
Unsupervised real world super resolution (USR) aims to restore high-resolution (HR) images given low-resolution (LR) inputs, and its difficulty stems from the absence of paired dataset. One of the most common approaches is synthesizing noisy LR images using GANs (i.e., degradation generators) and utilizing a synthetic dataset to train the model in a supervised manner. Although the goal of training the degradation generator is to approximate the distribution of LR images given a HR image, previous works have heavily relied on the unrealistic assumption that the conditional distribution is a delta function and learned the deterministic mapping from the HR image to a LR image. In this paper, we show that we can improve the performance of USR models by relaxing the assumption and propose to train the probabilistic degradation generator. Our probabilistic degradation generator can be viewed as a deep hierarchical latent variable model and is more suitable for modeling the complex conditional distribution. We also reveal the notable connection with the noise injection of StyleGAN. Furthermore, we train multiple degradation generators to improve the mode coverage and apply collaborative learning for ease of training. We outperform several baselines on benchmark datasets in terms of PSNR and SSIM and demonstrate the robustness of our method on unseen data distribution. Code is available at https://github.com/sangyun884/MSSR.
- Open Access
- 24 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 8181-8194
Multiple Object Tracking via Feature Pyramid Siamese Networks
When multiple object tracking (MOT) based on the tracking-by-detection paradigm is implemented, the similarity metric between the current detections and existing tracks plays an essential role. Most of the MOT schemes based on a deep neural network (DNN) learn the similarity metric using a Siamese architecture, but the plain Siamese architecture might not be enough owing to its structural simplicity and lack of motion information. This study aims to propose a new MOT scheme to overcome the existing problems in the conventional MOTs. Feature Pyramid Siamese Network (FPSN) is proposed to address the structural simplicity. The FPSN is inspired by a feature pyramid network (FPN) and it extends the Siamese network by applying FPN to the plain Siamese architecture and by developing a new multi-level discriminative feature. A spatiotemporal motion feature is added to the FPSN to overcome the lack of motion information and to enhance the performance in MOT. Thus, FPSN-MOT considers not only the appearance feature but also motion information. Finally, FPSN-MOT is applied to the public MOT Challenge benchmark problems and its performance is compared to that of the other state-of-the-art MOT methods.
- 24 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 8181-8194
Open AccessMultiple Object Tracking via Feature Pyramid Siamese Networks
When multiple object tracking (MOT) based on the tracking-by-detection paradigm is implemented, the similarity metric between the current detections and existing tracks plays an essential role. Most of the MOT schemes based on a deep neural network (DNN) learn the similarity metric using a Siamese architecture, but the plain Siamese architecture might not be enough owing to its structural simplicity and lack of motion information. This study aims to propose a new MOT scheme to overcome the existing problems in the conventional MOTs. Feature Pyramid Siamese Network (FPSN) is proposed to address the structural simplicity. The FPSN is inspired by a feature pyramid network (FPN) and it extends the Siamese network by applying FPN to the plain Siamese architecture and by developing a new multi-level discriminative feature. A spatiotemporal motion feature is added to the FPSN to overcome the lack of motion information and to enhance the performance in MOT. Thus, FPSN-MOT considers not only the appearance feature but also motion information. Finally, FPSN-MOT is applied to the public MOT Challenge benchmark problems and its performance is compared to that of the other state-of-the-art MOT methods.