배완기 (Wan-Gi Bae)

학력: 경북대학교 컴퓨터학부 석사 (2025.08 졸업 예정)
  경북대학교 컴퓨터학부 학부 (2023.08 졸업)
주요 연구분야: 컴퓨터비전; 행동인식, 3D multi-modal neural reconstruction
   
  Email / GitHub
profile photo

Papers
ELLAR: An Action Recognition Dataset for Extremely Low-Light Conditions with Dual Gamma Adaptive Modulation

Minse Ha*, Wan-Gi Bae*, Geunyoung Bae, Jong Taek Lee†
*Equal contribution, †Corresponding Author

ACCV, 2024. 한국정보과학회 우수학술대회, Acceptance Rate: 32%

Project page

Introducing a dataset called ELLAR with more than 12k+ videos and proposing a method for tackling action recognition under extremely low-light conditions.