Computer Vision Machine Learning Lab
School of Computer Science and Engineering
Graduate School of Artificial Intelligence, Chung-Ang University
221 Hueksuk-Dong, Dongjak-gu, Seoul, 156-756, Korea
Computer Vision Machine Learning Lab
School of Computer Science and Engineering
Graduate School of Artificial Intelligence, Chung-Ang University
221 Hueksuk-Dong, Dongjak-gu, Seoul, 156-756, Korea
News [Click here for a full list]
- 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
Yujin 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
Dagyeong Na (Master Student) [Homepage]
Anomaly Detection and Prediction in Time-series Data
Jihee Yoon (Master Student) [Homepage]
Story to Image Generation
Yujin Han (Master Student) [Homepage]
3DGS
Junhee Cho (Master Student) [Homepage]
Large-scale 3DGS
Minjun Kim (Bachelor Student), Dongha Lee (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
- 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: 2021-0-01341, Artificial Intelligence Graduate School Program
* Equal contribution
- Occlusion-Robust Multi-Object Tracking with Adaptive Feature Management and Motion Compensation
Jin Hong, Yoojin Han, Junseok Kwon, IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS), Tainan, Taiwan, 2025 [pdf] [code]
ACK: 2021-0-01341, Artificial Intelligence Graduate School Program
- Lightweight Grounding Model Combining a CLIP-based Encoder With an Upsampling Decoder
Jihee Yoon, Seunga Lee, Haesol Jeong, Junseok Kwon, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, Nashville, USA, 2025
- 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] [Early Accept (top 9% of submissions)] [pdf] [code]
+ Corresponding authors
ACK: 2021-0-01341, Artificial Intelligence Graduate School Program
- diffMusic: A Multi-Stage Model for Contextually Aligned Music Generation from Visual Inputs
Jin Hong, Taeun Lee, and Junseok Kwon , 14th Asian Conference on Computer Vision (ACCV) Workshop, Oral presentation, Hanoi, Vietnam, 2024
- Towards Calibrated Robust Fine-Tuning of Vision-Language Models
Changdae Oh, Hyesu Lim, Mijoo Kim+, Dongyoon Han, Sangdoo Yun, Jaegul Choo, Alexander Hauptmann, Zhi-Qi Cheng, Kyungwoo Song, Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2024 [pdf]
+This work was done when she was working at Carnegie Mellon University.
- Optimizing Dataset Distillation Using DATM: Adjusting Learning Rate and Upper Bound
Minjun Kim, Junhee Cho, and Junseok Kwon, The 18th European Conference on Computer Vision (ECCV) Workshop, 4th place award, Dataset Distillation Challenge , Milano, Italy, 2024 [pdf]
- Satellite Image Dehazing Via Masked Image Modeling and Jigsaw Transformation
Guisik Kim , Choongsang Cho, and Junseok Kwon, The 18th European Conference on Computer Vision (ECCV) Workshop, Advances in Image Manipulation workshop and challenges , Milano, Italy, 2024 [pdf]
- Geometry-Preserved Image Editing
Taeeun Kwon, and Junseok Kwon, The 18th European Conference on Computer Vision (ECCV) Workshop, Milano, Italy, 2024
ACK: 2021-0-01341, Artificial Intelligence Graduate School Program