권혁준
연구분야: Weakly-/Semi-supervised Perception, 3D Vision, Domain Adaptation/Generalization, AI Personalization, Human-AI Collaboration

• WISH: Weakly Supervised Instance Segmentation using Heterogeneous Labels, IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2025

• From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation, IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2024

• TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight, The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024

김영빈
연구분야: 컴퓨터비전, 자연어처리, 딥러닝응용

• See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias, Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025

• UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation, Empirical Methods in Natural Language Processing (EMNLP), 2024

• Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation, Empirical Methods in Natural Language Processing (EMNLP), 2024

김태용
연구분야: 스마트 인터랙션, 컴퓨터게임, 인공지능

• A hybrid approach of neural networks for age and gender classification through decision fusion, Biomedical Signal Processing and Control, 66, 2021

• Facial Expression Recognition by Regional Weighting with Approximated Q-learning, Symmetry, 12, 2020.02

• A Differential Evolution Approach to Optimize Weights of Dynamic Time Warping for Multi-Sensor Based Gesture Recognition, Sensors, Vol.19, 2019.3.

김학구
연구분야: 3D/VR, 생성형AI, 멀티모달

• MemoryTalker: Personalized Speech-Driven 3D Facial Animation via Audio-Guided Stylization, International Conference on Computer Vision 2025 (ICCV), 2025

•  Learning Phonetic Context-Dependent Viseme for Enhancing Speech-Driven 3D Facial Animation, Interspeech 2025

• Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection, IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2024

박진완
연구분야: 예술공학, 미디어아트, 멀티미디어

• The dépaysement art of the new media era incorporating the microscopic world, Digital Creativity, Vol. 32, No. 2, 2021

• Secrets of Balanced Composition as Seen through a Painter’s Window: Visual Analyses of Paintings Based on Subset Barycenter Patterns, Leonardo, Vol. 52, No. 4, pp. 364–373, 2019

• SIGGRAPH in Asia 2013 Hong Kong, Art Gallery: Paint Wall

박진휘
연구분야: Computer Vision, Machine Learning, Interdisciplinarity

• Test-Time Prompt Tuning for Zero-Shot Depth Completion, International Conference on Computer Vision 2025 (ICCV), 2025

• A Simple yet Universal Framework for Depth Completion, The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024

• Depth Prompting for Sensor-agnostic Depth Estimation, IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2024

백준기
연구분야: AI Imaging, Computational Photography, Lightfield, 영상복원 및 개선, 컴퓨터시각, 3차원시각

• HLDNet: Abandoned Object Detection Using Hand Luggage Detection Network. IEEE Consumer Electronics Magazine, vol. 11, no. 4, pp. 45-56, July 2022.

• Camera Orientation Estimation Using Motion-Based Vanishing Point Detection for Advanced Driving Assistance System" IEEE Trans. Intelligent Transportation Systems, vol. 22, no. 10, pp. 6286-6296 October 2021.

• Radiance-Reflectance Combined Optimization and Structure-Guided L0-Norm for Single Image Dehazing,\" IEEE Trans. Multimedia, vol. 22, no. 1, pp. 30-44, January 2020.

엄찬호
연구분야: 컴퓨터비전, 딥러닝 모델 및 학습방법, 콘텐츠 인공지능

• DiffPS: Leveraging Prior Knowledge of Diffusion Model for Person Search, International Conference on Computer Vision 2025 (ICCV), 2025

• GOAL⚽: Global-local Object Alignment Learning, IEEE Conf. Computer Vision and Pattern Recognition (CVPR),2025

• Subnet-Aware Dynamic Supernet Training for Neural Architecture Search, IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2025

오지형
연구분야: 인공지능, 컴퓨터비전, 생성AI, 영상처리

• ∿ SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video, IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2025

• MoDec🎄-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splatting, IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2025

• 🍎 FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring, IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2024

채영호
연구분야: HCI, 모션캡쳐, 동작인식, CG/VR, 메타버스, UI/UX 컴퓨터 프로그래밍

• Scenario-based Sensed Human Motion Editing and Validation through the Motion-Sphere, IEEE Access, Volume 10, March 2022

• Angular Features-Based Human Action Recognition System for a Real Application with Subtle Unit Actions, IEEE Access, Volume 10, January 2022

• Kinematically Admissible Editing of the Measured Sensor Motion Data for Virtual Reconstruction of Plausible Human Movements, IEEE SMC(System, Man and Cybernetics), 2021

최종원
연구분야: 컴퓨터비전, 딥페이크 탐지, 딥러닝 모델 및 학습방법, 콘텐츠 인공지능

• Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing, International Conference on Computer Vision 2025 (ICCV), 2025

•  Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection, International Conference on Computer Vision 2025 (ICCV), 2025

• InsideOut: Integrated RGB-Radiative Gaussian Splatting for Comprehensive 3D Object Representation, International Conference on Computer Vision 2025 (ICCV), 2025

한상임
연구분야: 미디어아트, 제너레이티브 아트, 3D CGI, 현대미술, 게임엔진

• Possibilities of the Virtual in Digital Space; Rethinking Bodies, Cognition, and Values in Metaverse, International Symposium on Electronic Arts (ISEA), 2022

•  Beyond Spatial Frequency: Pixel-wise Temp2024 “Digital Ecologies of the Self” International Conference on Videogame Science and Arts Game Lab Exhibition, Portugal

• QLD XR Festival 2024, Brisbane, Australia