Computer Vision Machine Learning Lab
School of Computer Science and Engineering
Graduate School of Artificial Intelligence, Chung-Ang University
Embedded Files
News [Click here for a full list]
- We have 1 paper accepted in AVSS 2026
- Yujin study at CMU as a visiting scholar (26/09~27/02)
- Dongha Lee has been accepted into the graduate program at Stanford University
- Jisoo will study at Imperial College London as a visiting scholar (26/08~27/02)
- Prof. Kwon serves as a Program Chair for KCCV 2026
- Prof. Kwon serves as an Area Chair for BMVC 2026
- We have 1 paper accepted in ICLR 2026
- We have 2 paper accepted in T-ASLP — Top-tier speech journal
- Prof. Kwon serves as an Area Chair for ECCV 2026 [Lead AC]
- We have 1 paper accepted in AAAI 2026 [Oral presentation]
- We have 1 paper accepted in ICDM 2025 [Oral presentation]
- Jin Hong and Yujin Han have been received Excellent Paper Award in AVSS 2025
- Prof. Kwon serves as an Area Chair for CVPR 2026 [Lead AC]
- We have 1 paper accepted in ASRU 2025 — Our first paper in speech research
- Prof. Kwon serves as an Area Chair for AAAI 2026
- Prof. Kwon serves as an Area Chair for WACV 2026
- We have 1 paper accepted in AVSS 2025
- We have 1 paper accepted in CVPR 2025 Workshop
- We have 1 paper accepted in MICCAI 2025 [Early Accept (top 9% of submissions)]
- Dr. Sungwoo Park will join Korea University as an Assistant Professor starting in March 2025
- We have 1 paper accepted in AAAI 2025
- Prof. Kwon serves as an Area Chair for ICCV 2025
- Prof. Kwon serves as an Area Chair for CVPR 2025
Members
Junseok Kwon (Professor) [Homepage] [Google Scholar]
Jinhee Park (Ph.D. Student) [Homepage]
Metric Learning, Confidence Calibration
Jin Hong (Ph.D. Student) [Homepage]
Image to Music Generation, Speech, Diffusion Model
Juhyeon Park (Ph.D. Student) [Homepage]
Multi-modal Learning
Youjin Kim (Ph.D. Student) [Homepage]
Physic-informed NN, Neural Operator, Geometric Learning
Jisoo Park (Ph.D.Student) [Homepage]
Speech, 3D Talking Head Synthesis, Deepfake Detection
Seonghak Lee (Ph.D. Student) [Homepage]
3D Human Avatar, 3D Talking Head Synthesis, Speech Enhancement
Sehong Oh (Ph.D. Student) [Homepage]
LLM
Jihee Yoon (Master Student) [Homepage]
Story to Image Generation
Yoojin Han (Master Student) [Homepage]
3D Language Field
Junhee Cho (Master Student) [Homepage]
3D Human Avatar, 3DGS
Woojin Kim (Master Student) [Homepage]
Computer Vision Machine Learning
Seongsoo Jeon (Master Student) [Homepage]
Computer Vision Machine Learning
Sol Lee (Bachelor Student), Gyubeom Kim (Bachelor Student), Hyeon Jegal (Bachelor Student), Haesol Jung (Bachelor Student), Sumin Han (Bachelor Student)
Alumni [Click here for a full list]
Recent & Selected Publications [Click here (Conference) and here (Journal) for a full list]
- Machine learning: Confidence Calibration, Out-Of-Distribution Detection, Metric learning, Geometric Learning, Adversarial Attack, Representation Learning, Monte Carlo sampling, Variational inference, Generative learning, Graph learning, and Meta learning,
- Computer vision: Diffusion Model, NeRF, 3D Talking Head Synthesis, HumanRF, Object detection, 3D Point clouds, Event summarization, Dehazing, and Low-light enhancement
- Speech: Speech Separation, Speech Enhancement, Speech Recognition
- Calibration-Free Multi-Object Tracking via Scale-Invariant Topological Depth and Adaptive Uncertainty Gating
Jin Hong, Yoojin Han, Junseok Kwon, IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS), Lecce, Italy, 2026
ACK: RS-2021II211341
- WildTalker ∞ : Pushing the Limits of 3D Talking Portrait Synthesis in Unconstrained Environments
Seonghak Lee*, Jisoo Park*, and Junseok Kwon, IEEE Transactions on Audio, Speech and Language Processing (T-ASLP), vol. 34, pp. 1259-1271, 2026 [pdf] [code]
Equal contribution
ACK: RS-2021II211341, Chung-Ang University Graduate Research Scholarship
- Spectral-guided Physical Dynamics Distillation
Youjin Kim, Dagyeong Na, Jae Yong Lee+, Junseok Kwon+, The Fourteenth International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, 2026 [pdf] [code]
+ Corresponding authors
ACK: RS-2021II211341, RS-2025-02217071, RS-2025-25422680
- DiffMusic: Efficient Music Generation From a Single Image Using Diffusion-Based Representations
Jin Hong, Juhyeon Park, and Junseok Kwon, IEEE Transactions on Audio, Speech and Language Processing (T-ASLP), vol. 34, pp. 1126-1136, 2026 [pdf] [code]
ACK: RS-2021II211341, Chung-Ang University Graduate Research Scholarship
- Neural Collapse-Informed Initialization with Perturbation Injection in Classification-based Metric Learning
Jinhee Park*, Hee Bin Yoo*, Minjun Kim, Byoung-Tak Zhang, and Junseok Kwon, Association for the Advancement of Artificial Intelligence (AAAI), Singapore, 2026 [pdf] [code]
[Oral presentation]
Equal contribution
ACK: RS-2021II211341
- Lightweight Wasserstein Audio-Visual Model for Unified Speech Enhancement and Separation
Jisoo Park*, Seonghak Lee*, Guisik Kim, Taewoo Kim, Junseok Kwon, IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Honolulu, Hawaii, USA, 2025 [pdf] [code]
ACK: RS-2021II211341
* Equal contribution
- Physics-Informed Neural Operators for Tissue Elasticity Reconstruction
Youjin Kim, Jae Yong Lee+, Junseok Kwon+, Medical Image Computing and Computer Assisted Intervention (MICCAI), Daejeon, Seoul, 2025 [pdf] [code]
[Early Accept (top 9% of submissions)]
+ Corresponding authors
ACK: RS-2021II211341
Page updated
Google Sites
Report abuse