Hi 👋, welcome!

I am an AI researcher. My main topics of interest are semantic segmentation, few-shot learning, implicit neural representation, neural compression, and 3D computer graphics.

🚀 I’m always excited to collaborate on innovative projects! Feel free to reach out to me at my email.

Awards

• 1st Winner of “AI4EO Map Your City Challenge” (2024)
• 4th Winner of “OpenEarthMap Land Cover Mapping Few-Shot Challenge” (2024)

Selected Publications

	Fourier-Modulated Implicit Neural Representation for Multispectral Satellite Image Compression Woojin Cho*, Steve Andreas Immanuel*, Junhyuk Heo, and Darongsae Kwon *Equal contribution IEEE International Geoscience and Remote Sensing Symposium (Oral), 2025
	Tackling Few-Shot Segmentation in Remote Sensing via Inpainting Diffusion Model Steve Andreas Immanuel, Woojin Cho, Junhyuk Heo, and Darongsae Kwon ICLR Machine Learning for Remote Sensing Workshop (Best Paper Award), 2025
	Neural Compression for Multispectral Satellite Images Woojin Cho*, Steve Andreas Immanuel*, Junhyuk Heo, and Darongsae Kwon *Equal contribution NeurIPS Neural Compression Workshop, 2024
	Learnable Prompt for Few-Shot Semantic Segmentation in Remote Sensing Domain Steve Andreas Immanuel and Hagai Raja Sinullinga CVPR Learning with Limited Data Workshop, 2024
	Lightweight Recurrent Cross-modal Encoder for Video Question Answering Steve Andreas Immanuel and Cheol Jeong Knowledge-Based System, 2023
	Improving distinctiveness in video captioning with text-video similarity Vania Velda, Steve Andreas Immanuel, Willy Fitra Hendria, and Cheol Jeong Image and Vision Computing, 2023

Misc

Peer Review

• IEEE Transactions on Geoscience and Remote Sensing
• Knowledge-Based Systems
• Image and Vision Computing

ESA-NASA International Workshop on AI Foundation Model for EO

1-page abstract paper (co-author):

• Multi-Modal Foundation Model for Electro-Optical and SAR Images using Neural Operator-Based CLIP
• A Unified Framework for Multi-Resolution and Multi-Spectral Satellite Imagery in Foundation Model Training
• Leveraging Few-Shot Learning and Data Augmentation for Scrap Metal Segmentation in Satellite Imagery
• Neural Representation-Based Foundation Model for Satellite Images Pansharpening
• Continual Pretraining for Satellite Imagery: A Foundation Model Framework with LLM Agents