Yoonsik Kim

Seoul National University — South Korea

Computer Science · Physical Sciences

16h-index1.1kcitations121works0.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Handwritten Text Recognition Techniques(13), Engineering Applied Research(13), Computational Fluid Dynamics and Aerodynamics(11), Advanced Image Processing Techniques(11), Image and Signal Denoising Methods(10)

Publications121 total

Evolution and Applications of Codeless AI Model Generation Tools for AI-Driven Education
2025
AmFall: WiFi CSI Amplitude-Based Fall Detection Using Denoised Scalograms
IEEE Internet of Things Journal·2025· 1 cited
TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains
arXiv (Cornell University)·2024Open Access
SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap
2023· 2 cited
SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap
arXiv (Cornell University)·2023Open Access
Towards Unified Scene Text Spotting Based on Sequence Generation
2023· 25 cited
Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
arXiv (Cornell University)·2023Open Access
Towards Unified Scene Text Spotting based on Sequence Generation
arXiv (Cornell University)·2023· 1 citedOpen Access
On Web-based Visual Corpus Construction for Visual Document Understanding
Lecture notes in computer science·2023· 2 cited
Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
2023· 1 citedOpen Access
On Web-based Visual Corpus Construction for Visual Document Understanding
arXiv (Cornell University)·2022Open Access
DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting
arXiv (Cornell University)·2022· 6 citedOpen Access
Multi-modal Text Recognition Networks: Interactive Enhancements Between Visual and Semantic Features
Lecture notes in computer science·2022· 68 cited
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
arXiv (Cornell University)·2021· 3 citedOpen Access
RewriteNet: Reliable Scene Text Editing with Implicit Decomposition of Text Contents and Styles
arXiv (Cornell University)·2021· 1 citedOpen Access
RewriteNet: Realistic Scene Text Image Generation via Editing Text in Real-world Image
arXiv (Cornell University)·2021· 6 citedOpen Access
SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text\n Recognition Models
arXiv (Cornell University)·2021Open Access
SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models
Lecture notes in computer science·2021· 2 citedOpen Access
Parallel operation control system of low-duty compressor and forcing vaporizer for liquefied natural gas carrier
Han-guk marin enjinieoring hakoeji·2020Open Access
Recognition of Assembly Instructions Based on Geometric Feature and Text Recognition
2020· 2 cited
page 1 of 7Next →

Frequent Co-authors

Nam Ik Cho(16), Jae Woong Soh(6), Jin Kim(5), Byeongyong Ahn(4), Kwang-Soo Kim(4), Kyoung-Kuk Yoon(4), Gu Yong Park(3), Sungrae Park(3), Soo Hyung Park(3), Jang Hyuk Kwon(3), Insung Hwang(3), Taeho Kil(3), Seonghyun Kim(3), En Sup Yoon(3), Suak‐Ho Van(3), Chul‐Ho Kim(3), Jaewoo Park(2), Isaac Kang(2), Hyun-Seung Lee(2), Young-Su Moon(2)