Sangyun Lee
Research Publications Projects People Courses News Hobbies
한국어

News

  • Jan 2026

    “Empowering Transformers Spectrally: Towards Comprehensive Pattern Learning for Image Demoiréing” was accepted to ICASSP 2026 (Barcelona, Spain).

  • Sep 2025

    “StoneGAT: A Robust Fall Detection Framework via Skeleton-aware Graph Attention Networks” was accepted to the International Journal of Control, Automation, and Systems (IJCAS).

  • Sep 2025

    A new project, “A Study on Vision-Language-based Multi-Object Tracking,” began, supported by the Sungkonghoe University Research Grant 2025.

  • Aug 2025

    “StoneGAT: Skeleton-aware Graph Attention Networks for Robust Fall Detection from Single-frame Poses” was accepted to ICCAS 2025 (Incheon, Korea).

  • May 2025

    “Feature Refinement with Vision State Space Modules for Tiny Object Detection” was accepted to the Journal of Institute of Control, Robotics and Systems (ICROS).

  • Dec 2024

    “DeepCampus: A Campus Tour Mobile Application Using Deep Learning-Based Vision Technologies” was accepted to the Transactions of the Korean Institute of Electrical Engineers (KIEE).

  • Nov 2024

    “Making MambaVision Temporal: Leveraging TSM for Efficient Video Understanding” was accepted to ICEIC 2025 (Osaka, Japan).

  • Aug 2024

    A new project, “Making Action Detection Practical: Leveraging 2D CNNs for Real-Time and Online Applications,” began, supported by the Sungkonghoe University Research Grant 2024.

  • Jul 2024

    A new project on real-time video-AI monitoring of hazardous situations for industrial workers began, supported by the Ministry of SMEs and Startups / TIPA (Korea).

  • Dec 2023

    “Making TSM Better: Preserving Foundational Philosophy for Efficient Action Recognition” was accepted to ICT Express.

  • May 2023

    A new project, “Development of Core Technology for Preventing Identity Theft,” began, supported by SECUCHART GLOBAL Co., Ltd.

  • Apr 2023

    “D-TSM: Discriminative Temporal Shift Module for Action Recognition” was accepted to UR 2023 (Hawaii, USA).

  • Oct 2022

    “Extended Siamese Convolutional Neural Networks for Discriminative Feature Learning” was accepted to the International Journal of Fuzzy Logic and Intelligent Systems (IJFIS).

  • Aug 2022

    A new project, “A Context-aware Multiple Object Tracking with Temporal Shifted Transformer,” began, supported by the Sungkonghoe University Research Grant 2022.

  • Mar 2022

    A new project on AI integration technology for comprehensive context-aware multiple object tracking began, supported by the Ministry of Science and ICT / NRF.

© 2026 Sangyun Lee Built with Astro. Hosted on GitHub Pages.