Jamo Is All You Need: Enhancing Korean OCR with Style Tags
Younguk Kim (Electrical Engineering)
Seokhoon Kang (Architecture) Ye Ji Chun (Data Science) Juhee Chae (Engineering Practice) [paper] |
|
Jamo Is All You Need: Enhancing Korean OCR with Style Tags
Younguk Kim (Electrical Engineering)
Seokhoon Kang (Architecture) Ye Ji Chun (Data Science) Juhee Chae (Engineering Practice) [paper] |
|
Action-Segmentation based Gaze Anticipation on Egocentric Video
Sebin Lee (Artificial Intelligence)
Jaewoo Park (Data Science) Jiwon Lee (Electrical Engineering) Yerang Mok (Aerospace Engineering) [paper] |
|
Learning Semantic Representations for Video Summarization via MLLMs
Sumin Kim (Data Science)
Minjun Kim (Computer Science) Wonsik Shin (Artificial Intelligence) Yebonn Han (Math Education) [paper] |
|
FluidGPT: Towards Fluid Dynamics Reasoning in Vision-Language Models
Jusang Oh (Electrical Engineering)
Soeon Park (Materials Science & Engineering) Jason Park (Electrical Engineering) Kangsun Lee (Electrical Engineering) [paper] |
|
Multimodal Multi-Camera Timecode Synchronization via Audio-visual Embeddings
Hyogul Yang (Economics)
Heungchan Kwon (Electrical Engineering) Junhyeong Park (Data Science) Wonjin Cho (Artificial Intelligence) [paper] |
|
Semantic Coherence-Aware Evidence Filtering for Retrieval-Augmented VQA
Sung Geun An (Data Science)
Gyeongseop Lee (Engineering Practice) Jooyoung Kim (Data Science) [paper] |
|
Decomposing Text into Motion and Appearance for Controllable Human Video Generation
Sungho Bae (Data Science)
Sanghwa Hong (Artificial Intelligence) Sangbum Lee (Aerospace Engineering) Boyeong Im (Data Science) [paper] |
|
FEBench: Multi-dimensional Facial Editing Benchmark
Dongsoo Shin (Data Science)
Shihyung Park (Artificial Intelligence) Seohee Kim (Applied Bioengineering) [paper] |
|
A Multi-stage Validation Framework for Cross-Subject EEG-to-Video Reconstruction
Ahhyun Lucy Lee (Brain & Cognitive Science)
Minchan Kim (Data Science) Shakhnoza Khojimatova (Data Science) Wooseok Lee (Data Science) [paper] |
|
Echo-Enhanced ECG: Bridging Vision and Physiological Signal via Representation Learning
Jongui Chai (Bioinformatics)
Jinyong Kim (Artificial Intelligence) Jonggeun Lee (Artificial Intelligence) [paper] |
|
A Single Word Bypass: How Name Tokens Break Data Protection
Mijin Koo (Intelligence and Information)
Changhee Cho (Data Science) Yongmo Kwon (Artificial Intellgience) [paper] |
|
 |
Bldg 942-422, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Korea. Copyright (c) 2021, Visual Information Processing Lab, Graduate School of Data Science, Seoul National University, All Rights Reserved. |