Jae-Woo Kim

I'm a Ph.D. student at ACSL @ GIST AI, advised by Prof. Ue-Hwan Kim. My research interest is scene analysis (change detection & captioning) and machine learning for computer vision.

Email  /  Google Scholar  /  Semantic Scholar  /  LinkedIn  /  Github

Published Papers

2026

• Bounded Temporal Support for Robot Place Recognition
  Seon-Mo Kim*, Jae-Woo Kim*, Yeon-Hyuk Kim, Ue-Hwan Kim
  Preprint
• C3-Bench: A Context-Aware Change Captioning Benchmark
  Jae-Woo Kim, Hyeongbeom Kim, Ue-Hwan Kim
  European Conference on Computer Vision (ECCV) 2026 [code] [dataset]
• MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environments
  Yi-rum Kim, Jae-Woo Kim, Ue-Hwan Kim
  IEEE International Conference on Robotics & Automation (ICRA) 2026

2025

• Towards Generalizable Scene Change Detection
  Jae-Woo Kim, Ue-Hwan Kim
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025 [code] [dataset]

2023

• Adaptively Marginalizing Cosine Logits for Effectively Learning Deep Visual Place Representation in Loop Closure Detection
  Jae-Woo Kim, Ue-Hwan Kim
  International Conference on Robot Intelligence Technology and Applications (RiTA) 2023
• Efficient Data Grouping for Large-Scale Visual Place Recognition Dataset
  Jae-Woo Kim, Ue-Hwan Kim
  International Conference on Robot Intelligence Technology and Applications (RiTA) 2023

• Best Bachelor Thesis Award - GIST 2023

• Selected as GIST College Presidential Scholarship - GIST 2023

This template is from Jon Barron.