Sungho Suh (서승호)
Senior Researcher
German Research Center for Artificial Intelligence (DFKI)
and
RPTU Kaiserslautern-Landau
German Research Center for Artificial Intelligence (DFKI)
and
RPTU Kaiserslautern-Landau
I'm a Researcher working on Human-Centric Multimodal AI for smart living.
I am a Senior Researcher at DFKI and RPTU. I am interested in multimodal AI, generative models, and physics-informed neural networks with a focus on industrial applications, such as human activity recognition using wearable sensors, predictive maintenance, remaining useful life prediction of Lithium-ion batteries, virtual try-on for online clothing shopping, and biomedical imaging.
Education
Ph.D. in Computer Science, Technische Universität Kaiserslautern (TUK), Germany, 2021 (Magna Cum Laude)
M.S. in Electrical Engineering and Computer Science, Seoul National University, Republic of Korea, 2011
B.S. in Electrical and Computer Engineering, Seoul National University, Republic of Korea, 2009
Work Experience
Senior Researcher, German Research Center for Artificial Intelligence (DFKI), Germany, Mar 2021 - Present
Wissenschaftlicher Mitarbeiter and Lecturer, RPTU Kaiserslautern-Landau, Germany, Apr 2022 - Present
Doctoral Researcher, KIST Europe, Germany, Mar 2018 - Feb 2021
Research Engineer, Samsung Electro-Mechanics, Republic of Korea, Aug 2011 - Mar 2018
News
[04. 2024] We will organize a workshop in IJCAI-24, Jeju, Korea! Link
- The 4th International Workshop on Deep Learning for Human Activity Recognition[03. 2024] Our paper has been accepted in Frontier in Computer Science!
- A Comprehensive Evaluation of Marker-Based, Markerless Methods for Loose Garment Scenarios in Varying Camera Configurations[03. 2024] Our paper has been accepted in Knowledge-Based Systems, Elsevier (IF 8.8)
- AI-KD: Adversarial learning and Implicit regularization for self-Knowledge Distillation [arXiv][03. 2024] We received the Best Runner-Up WIP Award at the IEEE PerCom 2024!
- Text me the data: Generating Ground Pressure Sequence from Textual Descriptions for HAR [arXiv][02. 2024] Our open-access book with many colleagues from the STAR project is now published!
- "Artificial Intelligence in Manufacturing". Download free at: https://link.springer.com/book/10.1007/978-3-031-46452-2[02. 2024] We received the Best Paper Award at the 18th EAI BODYNETS 2023!
- Real-Time and on-the-Edge Multiple Channel Capacitive and Inertial Fusion-Based Glove[01. 2024] A tutorial has been presented and two papers have been presented in the ICEIC 2024.
- Fault Diagnosis of Indium Tin Oxide Electrodes by Multi-Channel S-Parameter Patterns (Best Paper Award Bronze Prize)
- Image Generation of Ultra-Thin Polymer Films Using Diffusion Models From Tensile Testing for Mechanical Failure Prediction[12. 2023] Our paper has been accepted in Engineering Applications of Artificial Intelligence, Elsevier (IF 8.0)
- ContextMix: A context-aware data augmentation method for industrial visual inspection systems[12. 2023] Our paper has been accepted in the IEEE ICASSP 2024, Seoul Republic of Korea.
- A Novel Local-Global Feature Fusion Framework for Body-weight Exercise Recognition with Pressure Mapping Sensors[11. 2023] Our two papers have been accepted in the AAAI workshop Sustainable AI
- CoSS: Co-optimizing Sensor and Sampling Rate for Data-Efficient AI in Human Activity Recognition
- The Power of Training: How Different Neural Network Setups Influence the Energy Demand[11. 2023] Our paper has been accepted in the IEEE Internet of Things (IF 10.6)
- Worker Activity Recognition in Manufacturing Line Using Near-body Electric Field