Scholar
Seungryul Baek
Google Scholar ID: Mz1fab8AAAAJ
Associate Professor, UNIST
Citations & Impact
Citations
1,669
H-index
17
i10-index
21
Publications
20
Co-authors
65
list available
Publications
Resume (English only)
Academic Achievements
- - 'B-RIGHT: Benchmark Re-evaluation for Integrity in Generalized Human-Object Interaction Testing', Yoojin Jang et al., BMVC 2025 (accepted).
- - 'Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection', Taehoon Kim et al., ICCV 2025 (accepted).
- - 'BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting', Jeongwan On et al., CVPR 2025.
- - 'PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation', Uyoung Jeong et al., CVPR 2025.
Research Experience
- - Associate Professor, Ulsan National Institute of Science and Technology (UNIST), AI Graduate School and Dept. of CSE, Mar. 2024 ~ (Present).
- - Assistant Professor, Ulsan National Institute of Science and Technology (UNIST), AI Graduate School and Dept. of CSE, Apr. 2020 ~ Feb. 2024.
- - Student Internship, INRIA Sophia Antipolis, Valbonne, France. Advisor: François Brémond, Jun. 2019 ~ Aug. 2019.
- - Computer Vision Engineer, Samsung Electronics, DMC Research, Suwon, South Korea. This job is taken as the alternative to the military duties in South Korea. Feb. 2011 ~ Feb. 2015.
Education
- - Ph.D., Dept. of Electrical and Electronic Engineering, Imperial College London, London, UK. Advisor: Tae-Kyun Kim, Sep. 2015 ~ Mar. 2020.
- - M.S., Dept. of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea. Advisor: Chang D. Yoo, Feb. 2009 ~ Feb. 2011.
- - B.S., Dept. of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea. Mar. 2004 ~ Jan. 2009.
Background
- Research Interests: Computer Vision and Machine Learning (Deep Learning). Specifically, 3D Pose Estimation/Mesh Reconstruction, Action/Gesture Recognition, Semantic Segmentation, Object Recognition.
Miscellany
- Personal interests not provided.
