Junuk Cha
Scholar

Junuk Cha

Google Scholar ID: DmTVKDIAAAAJ
KAIST
Deep Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
162
 
H-index
6
 
i10-index
5
 
Publications
16
 
Co-authors
0
 
Contact
Emailjunukcha@kaist.ac.krTwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
4 items
OpenFS: Multi-Hand-Capable Fingerspelling Recognition with Implicit Signing-Hand Detection and Frame-Wise Letter-Conditioned Synthesis
2026
Cited
0
CoT-Pose: Chain-of-Thought Reasoning for 3D Pose Generation from Abstract Prompts
2025
Cited
0
BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting
2025
Cited
0
EmoTalkingGaussian: Continuous Emotion-conditioned Talking Head Synthesis
2025
Cited
0
Resume
Academic Achievements
  • CoT-Pose: Chain-of-Thought Reasoning for 3D Pose Generation from Abstract Prompts (ICCV 2025 workshop), equal contribution
  • BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting (CVPR 2025)
  • EmoTalkingGaussian: Continuous Emotion‑conditioned Talking Head Synthesis (arXiv 2025)
  • Text2Relight: Creative Portrait Relighting with Text Guidance (AAAI 2025), co-last author
  • 3DGS-based Bimanual Category-agnostic Interaction Reconstruction (ECCV 2024 Technical Report); 1st place in the associated challenge
  • Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction (CVPR 2024), co-last author
  • VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model (CVPR)