Skip to content
View SkiddieAhn's full-sized avatar

Block or report SkiddieAhn

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
SkiddieAhn/README.md

👋 Welcome to SKD's Github

  • ML Research Engineer at PYLER, focused on multimodal deep learning, computer vision, and video understanding.
  • Received a Bachelor's degree in Computer Science from The Catholic Univerity of Korea, with Magna Cum Laude.
  • Received a Master's degree in Computer Science from Yonsei University, advised by Prof. Sanghyun Park.

GitHub stats

🏙 Experience

PYLER

ML Research Enginner (2025.07 ~ present)
Technical Research Personnel

  • Multimodal Deep Learning
  • Video Understanding

Data Engineering Lab

AI Researcher (2022.03 ~ 2025.05)
Yonsei Univ. Dept of Computer Science

  • Video Anomaly Detection
  • Medical Image Segmentation

📜 Publications

International Papers
  1. Sunghyun Ahn*, Youngwan Jo*, Kijung Lee, Sein Kwon, Inpyo Hong, and Sanghyun Park. (*equally contributed) "AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM" arXiv, Preprint [View][Code]
  2. Inpyo Hong, Youngwan Jo, Hyojeong Lee, Sunghyun Ahn, and Sanghyun Park. "GranQ: Granular Zero-Shot Quantization with Channel-Wise Activation Scaling in QAT" arXiv, Preprint [View]
  3. Kijung Lee, Youngwan Jo, Sunghyun Ahn, and Sanghyun Park. "MDVAD: Multimodal Diffusion for Video Anomaly Detection" Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), regular paper, June 2025. (BK, IF=1) [View]
  4. Inpyo Hong, Youngwan Jo, Hyojeong Lee, Sunghyun Ahn, and Sanghyun Park. "Advanced Knowledge Transfer: Refined Feature Distillation for Zero-Shot Quantization in Edge Computing" ACM/SIGAPP Symposium On Applied Computing (SAC), regular paper, Mar 2025. (BK, IF=1) [View]
  5. Sunghyun Ahn, Youngwan Jo, Kijung Lee, and Sanghyun Park. "VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection" Asian Conference on Computer Vision (ACCV), regular paper, Sep 2024. (BK, IF=1) [View][Code]
  6. [SCIE] Seungkyun Hong*, Sunghyun Ahn*, Youngwan Jo, and Sanghyun Park. (*equally contributed) "Making Anomalies More Anomalous: Video Anomaly Detection Using a Novel Generator and Destroyer" IEEE Access (2024): 36712-36726. (IF: 3.9, JCR: Q2) [View][Code]
  7. Seungkyun Hong*, Sunghyun Ahn*, Youngwan Jo, and Sanghyun Park. (*equally contributed) "Dual Stream Fusion U-Net Transformers for 3D Medical Image Segmentation" IEEE International Conference on Big Data and Smart Computing (BigComp), regular paper, Feb 2024. [View][Code]
Domestic Papers
  1. 안성현, 조영완, 이기정, 권세인 and 박상현. "Anomaly LVLM: LVLM을 활용한 사용자 맞춤형 비디오 이상 탐지 연구" 한국정보과학회 학술발표논문집 (2024): 120-122. [View] 🏆
  2. 김은지, 안성현, 이효정 and 박상현. "MSPD: 자기 지도 학습 기반 저선량 CT 디노이징을 위한 다해상도 픽셀 무작위 배열 다운샘플링 네트워크" 한국정보과학회 학술발표논문집 (2024): 123-125. [View]
  3. 홍인표, 조영완, 안성현, 김은지, 권세인 and 박상현. "DQ-ResUNet: 의료 영상 분할의 효율성 개선을 위한 동적 양자화 기반 최적화" 한국정보과학회 학술발표논문집 (2024): 708-710. [View]
  4. 이기정, 안성현, 김현진 and 박상현. "FFAE: 비디오 이상 탐지를 위한 비디오 프레임 전처리 및 특징 융합 방법" 한국정보과학회 학술발표논문집 (2023): 526-528. [View]
  5. 안성현, 김환희, 권세인 and 박상현. "C-Swin UNETR: 3D 의료 영상 분할을 위한 채널 어텐션이 적용된 Swin Transformer" 한국정보과학회 학술발표논문집 (2023): 787-789. [View]
  6. 안성현, 조영완, and 박상현. "다중 객체 비디오에서의 어텐션 기반 단일 객체 추적 모델 연구" 한국정보과학회 학술발표논문집 (2022): 628-630. [View]
International Patents
  1. Kijung Lee, Youngwan Jo, Sunghyun Ahn, and Sanghyun Park. "Method of Detecting Video Anomaly on the Basis of Multimodal Diffusion and Device Therefor" ID: 19/078,589 (2025). [View]
  2. Seungkyun Hong, Sunghyun Ahn, Youngwan Jo, and Sanghyun Park. "Image segmentation method using dual attention and the device utilizing it" ID: PCT/KR2023/020370 (2023). [View]
Domestic Patents
  1. 이기정, 조영완, 안성현, and 박상현. "다중모달 확산 기반의 비디오 이상 탐지 방법 및 장치" ID: 10-2024-0055081 (2024). [View]
  2. 홍승균, 안성현, 조영완, and 박상현. "F2LM 기반의 비디오 이상 탐지 방법 및 장치" ID: 10-2024-0055080 (2024). [View]
  3. 홍승균, 안성현, 조영완, and 박상현. "이중 어텐션을 이용한 이미지 세그멘테이션 방법 및 이를 활용한 장치" ID: 10-2023-0124697 (2023). [View]

🤙 Contact

E-mail: skd@yonsei.ac.kr, CV: view, slide

Pinned Loading

  1. Paper-AnyAnomaly Paper-AnyAnomaly Public

    PyTorch Implementation of the Paper 'AnyAnomaly': Official Version

    Python 34 7

  2. Paper-VideoPatchCore Paper-VideoPatchCore Public

    [ACCV 2024] PyTorch Implementation of the Paper 'VideoPatchCore': Official Version

    Python 26 2

  3. Paper-Making-Anomalies-More-Anomalous Paper-Making-Anomalies-More-Anomalous Public

    [IEEE Access] PyTorch Implementation of the Paper 'Making Anomalies More Anomalous': Official Version

    Python 3 1

  4. Paper-DS-UNETR Paper-DS-UNETR Public

    [BigComp 2024] PyTorch Implementation of the Paper 'DS-UNETR': Official Version

    Jupyter Notebook