AI 원천기술연구 | 서울대학교AI연구원(AIIS)

연구

AI 원천기술연구

서울대학교 AI연구원은 AI의 난제를 해결할 수 있는 세계 최고 수준의 AI 원천기술 인력을
대규모로 보유하고 있는 국내 최대의 AI 연구기관입니다.

시각과 지각 (Vision & Perception)

인간의 시각과 청각을 모사하는 알고리듬을 연구합니다.
사진, 동영상, 그리고 인간의 특성을 인식하여 분류, 검출, 분석할 수 있는 기계학습 모델 개발하고 있습니다.

이종호공과대학 전기정보공학부

  • 연구실/전공분야Laboratory for the Imaging Science and Technology
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception
  • 연구분야(X+AI)Bio, Brain, Medicine

대표논문

Shin D, Ji S, Lee D, Lee J, Oh SH, Lee J*,
Deep Reinforcement Learning Designed RF Pulse: DeepRF_SLR
arXiv. 2019 Dec;1912.09015.
Jung W*, Steffen Bollmann*, Lee J*
[REVIEW] Overview of quantitative susceptibility mapping using deep learning – Current status, challenges and opportunities
arXiv. 2019 Dec;1912.05410.
Jung W, Yoon J, Ji S, Choi JY, Kim JM, Nam Y, Kim EY, Lee J*
Exploring linearity of deep neural network trained QSM: QSMnet+
Neuroimage 2020 in press
Lee J, Lee D, Choi JY, Shin D, Shin HG, Lee J*
Artificial neural network for myelin water imaging
Magn Res Med 2020 83(5):1875-1883
Yoon J, Gong E, Chatnuntawech I, Bilgic B, Lee J, Jung W, Ko J, Jung H, Setsompop K, Zaharchuk G, Kim EY, Pauly J, Lee J*
Quantitative susceptibility mapping using deep neural network: QSMnet
NeuroImage 2018 179:199-206

최세영치의학대학원 치의학과

  • 연구실/전공분야신경네트워크 연구실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception
  • 연구분야(X+AI)Brain, Medicine

대표논문

Kang MS, Choi TY, Ryu HG, Lee D, Lee SH, Choi SY*, Kim KT*. Autism-like behavior caused by deletion of vaccinia-related kinase 3 is improved by TrkB stimulation. J Exp Med. 2017 Oct 2;214(10):2947-2966. doi: 10.1084/jem.20160974.
Choi TY, Lee SH, Kim YJ, Bae JR, Lee KM, Jo Y, Kim SJ, Lee AR, Choi S, Choi LM, Bang SH, Song MR, Chung J, Lee KJ, Kim SH, Park CS, Choi SY. Cereblon maintains synaptic and cognitive function by regulating BK channel. J Neurosci. 2018 Apr 4;38(14):3571-3583. doi: 10.1523/JNEUROSCI.2081-17.2018.
Noh K, Lee H, Choi TY, Joo Y, Kim SJ, Kim H, Kim JY, Jahng JW, Lee S*, Choi SY*, Lee SJ*. Negr1 modulates anxiety- and depression-like behaviors via interaction with the LIF receptor and Lcn-2 expression. Mol Psychiatry. 2019 Aug;24(8):1189-1205. doi: 10.1038/s41380-018-0347-3.
Park SW, Kim J, Kang M, Lee W, Park BS, Kim H, Choi SY, Yang S, Ahn JH, Yang S. Epidermal electrotherapy for epilepsy. Small. 2018 Jul;14(30):e1801732. doi: 10.1002/smll.201801732.
An H, Cha KM, Choi SY, Shin HC. Data compression of excitatory postsynaptic potentials. Electronics Lett. 2015 Aug 31; 51(18):1407-1409. doi: 10.1049/el.2015.1133.
대뇌피질 신경회로의 기능적 다양성 및 발달기전 규명을 통한 뇌기능 이상 해법 도출 (과학기술정보통신부/중견연구자지원사업) 2016.06.01.-2019.05.31
Ex vivo 기반 해마체 신경망 다채널 분석 기술 개발 (과학기술정보통신부/뇌과학원천기술개발사업) 2013.05.01-2016.04.30

박주연생활과학대학 의류학과

  • 연구실/전공분야웨어러블인간공학
  • 연구분야(AI 원천기술)Vision & Perception, Human-AI Interaction, Data Intelligence
  • 연구분야(X+AI)Medicine, Commerce, Manufacturing

대표논문

Park, J. (2018). The effect of virtual body checking on self-image discrepancy, body dissatisfaction and weight regulation intention. Cyberpsychology: Journal of Psychosocial Research on Cyberspace, 12(1), Advanced Online Publication
Park, J. (2017). Emotional reactions to the 3D virtual body and future willingness: The effects of self-esteem and social physique anxiety. Virtual Reality, 22(1), 1-11.
Park, J., Ogle, J. P., & Shaver, J. (2019). Virtual avatar experience for the intervention of body image concerns.  Proceedings of the Seventy-sixth Annual Conference of the International Textile and Apparel Association, International Textile and Apparel Association. Retrieved from http://lib.dr.iastate.edu/itaa_proceedings/2019/
Park, J, & Langseth-Schmidt, K. (2016). Anthropometric fit evaluation of firefighters’ uniform pants: A sex comparison. International Journal of Industrial Ergonomics, 56, 1-8.
Conroy, B., & Park, J. (2018). Body armor fit and comfort using 3D body scanning: A collaborative industry project. Proceedings of the Seventy-fifth Annual Conference of the International Textile and Apparel Association, International Textile and Apparel Association. Retrieved from http://lib.dr.iastate.edu/itaa_proceedings/2018/
2D 촬영 정보로 인체 체형 분류 및 검증, 중소기업기술정보진흥원, 2019-06-26 ~ 2021-08-25
인간중심 소프트로봇기술 연구센터, 선도연구센터 (기초연구사업),  2020-01-01 ~ 2022-12-31

이규언의과대학 외과학교실

  • 연구실/전공분야유방내분비외과학
  • 연구분야(AI 원천기술)Vision & Perception, Autonomous Driving
  • 연구분야(X+AI)Medicine

대표논문

Ultrasound image analysis using deep learning algorithm for the diagnosis of thyroid nodules. Medicine (Baltimore). 2019
로봇수술 숙련도 평가 모델 및 트레이닝 시스템의 개발 및 적용 (한국연구재단 신진연구자지원사업, 2015~)
의료 빅데이터 융합 전문가 인력 양성을 위한 비정형 빅데이터의 정형화 기술 및 분석 플랫폼 개발(과학기술정보통신부, 정보통신방송연구개발사업, 세부책임자, 2019~)

이교구융합과학기술대학원 지능정보융합학과

  • 연구실/전공분야Music and Audio Research Group
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Language & Cognition
  • 연구분야(X+AI)Arts, Brain

대표논문

Hyeong-Seok Choi, Changdae Park, and Kyogu Lee, “From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from Speech”, to appear in Proceedings of International Conference on Learning epresentations (ICLR), 2020
Jie Hwan Lee, Hyeong-Seok Choi, and Kyogu Lee, “Audio query-based music source separation”, in Proceedings of International Society for Music Information Retrieval Conference (ISMIR), 2019
Juheon Lee, Hyeong-Seok Choi, Chang-bin Jeon, Junghyun Koo, and Kyogu Lee, “Adversarially Trained End-to-end Korean Singing Voice Synthesis System”, in Proceedings of Interspeech, 2019, Best Student Paper Award
Juheon Lee, Sungkyun Chang, Sangkeun Choe, and Kyogu Lee, “COVER SONG IDENTIFICATION USING SONG-TO-SONG CROSS-SIMILARITY MATRIX WITH CONVOLUTIONAL NEURAL NETWORK”, in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
Yoonchang Han, Jaehun Kim, Kyogu Lee, “Deep convolutional neural networks for predominant instrument recognition in polyphonic music”, IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol. 25(1), pp. 208-221, 2017
"자기회귀적 적대적 생성 신경망 기반의 가창 합성 및 평가 모델 연구", 미래창조과학부/전략과제, 2017.11.01~2020.10.31
"심상의 소리: 적대적 신경망을 활용한 크로스-모달 오디오 합성/변환 연구", 과학기술정보통신부/원천기술개발사업,  2017.11.01~2020.12.31
"뇌·인지 발달과정의 기초-영아단계 모사형 실세계 상호작용 경험 기반 객체 관련 개념의 기계학습 기술, 과학기술정보통신부/정보통신방송연구개발사업", 2019.04.01~2022.12.31

김현진공과대학 항공우주공학과

  • 연구실/전공분야자율로봇연구실
  • 연구분야(AI 원천기술)Vision & Perception, Robotics & Action, Autonomous Driving
  • 연구분야(X+AI)Logistics, Manufacturing

대표논문

Autonomous helicopter flight via reinforcement learning
HJ Kim, MI Jordan, S Sastry, AY Ng,  Advances in neural information processing systems, 2004
Aerial manipulation using a quadrotor with a two dof robotic arm
S Kim, S Choi, HJ Kim
IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013
Real-time monocular image-based 6-DoF localization
H Lim, SN Sinha, MF Cohen, M Uyttendaele, HJ Kim
International Journal of Robotics Research 34 (4-5), 476-492, 2015
Learning Transformable and Plannable se(3) Features for Scene Imitation of a Mobile Service Robot
J Park, J Kim, Y Jang, I Jang, HJ Kim
IEEE Robotics and Automation Letters, 2020
Fast and safe policy adaptation via alignment-based transfer
Jigang Kim, Seungwon Choi, and H. Jin Kim
IEEE/RSJ International Conference on Intelligent Robots and Systems, 2019

이재성의과대학 핵의학교실

  • 연구실/전공분야 핵의학 영상처리 / 정량 분석 
  • 연구분야(AI 원천기술)Vision & Perception
  • 연구분야(X+AI)Bio, Brain, Medicine

대표논문

Generation of PET attenuation map for whole-body time-of-flight 18F-FDG PET/MRI using a deep neural network trained with simultaneously reconstructed activity and attenuation maps. J Nucl Med. 2019 Aug;60(8):1183-1189.
Improving the accuracy of simultaneously reconstructed activity and attenuation maps using deep learning. J Nucl Med. 2018 Oct;59(10):1624-1629.
Deep-dose: a voxel dose estimation method using deep convolutional neural network for personalized internal dosimetry. Sci Rep. 2019; 9:10308.
Measurement of glomerular filtration rate using quantitative SPECT/CT and deep-learning-based kidney segmentation. Sci Rep. 2019;9:4223.
r amyloid PET using a deep learning approach. Hum Brain Mapp. 2018 May 11;39(9):3769–3778.
뇌질환 임상연구를 위한 7T MR-Compatible PET System 개발, 과학기술
정보통신부, 2014.07 - 2019.04
차세대 초저선량 PET 시스템 핵심 기술 개발, 과학기술 정보통신부, 2016.06 - 2021.03

김치헌의과대학 신경외과학교실

  • 연구실/전공분야신경외과학
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Data Intelligence
  • 연구분야(X+AI)Medicine, Manufacturing

대표논문

고형석공과대학 전기정보공학부

  • 연구실/전공분야그래픽스 및 미디어 연구실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception
  • 연구분야(X+AI)Manufacturing

대표논문

Wonseop Lee, Hyeong-Seok Ko. Heuristic misfit reduction: A programmable approach for 3D garment fit customization. Computer & Graphics, 71, 1-13.
Dong-Hoon Han, Ick-Hoon Cha, Kyung-Hyun Lee and Hyeong-Seok Ko. Garment Preconditioning and Regional Simulation Omission for Trying-On Virtual Ensembles. Computer Animation and Social Agents 2019.
Goanghun Kim and Hyeong-Seok Ko. A Practical Approach to Physically‐Based Reproduction of Diffusive Cosmetics. Computer Graphics Forum. Volume 37, Number 7.
CCTV 영상으로부터 3D 모델과 딥러닝 및 이미지 품질 개선 기술을 활용한 정면 얼굴 복원 기술 개발, 과학기술정보통신부, 2018~2023.
의류 직물의 3D 재현 연구. 한국연구재단. 2012~2015.
증강현실 기술을 이용한 실시간 매직미러 서비스 기술개발. 정보통신산업진흥원. 2012~2014.

권태경공과대학 컴퓨터공학부

  • 연구실/전공분야인터넷 융합 및 보안 연구실
  • 연구분야(AI 원천기술)Vision & Perception, Data Intelligence, AI Security
  • 연구분야(X+AI)Humanities/Social Sciences, Commerce

대표논문

"Magnetic Field based Indoor Localization System: A Crowdsourcing Approach",  International Conference on Indoor Positioning and Indoor Navigation (IPIN 2019), Pisa, Italy, September 2019
"Unveiling a Socio-Economic System in a Virtual World: A Case Study of an MMORPG", World Wide Web Conference (WWW) 2018 (Industry track), Lyon, France, April. 2018.
"Privacy Leakage in Event-based Social Networks: A Meetup Case Study", In Proceedings of ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW`18), Jersey City, United States, November 2018

서진욱공과대학 컴퓨터공학부

  • 연구실/전공분야휴먼-컴퓨터 인터액션 연구실
  • 연구분야(AI 원천기술)Vision & Perception, Human-AI Interaction, Data Intelligence
  • 연구분야(X+AI)Humanities/Social Sciences, Medicine, Manufacturing

대표논문

Jaemin Jo and Jinwook Seo, "Disentangled Representation of Data Distributions in Scatterplots," 2019 IEEE Visualization Conference (VIS), Vancouver, BC, Canada, 2019, pp. 136-140.
Daekyoung Jung, Wonjae Kim, Hyunjoo Song, Jeong-in Hwang, Bongshin Lee, Bohyoung Kim, and Jinwook Seo, ChartSense: Interactive Data Extraction from Chart Images, In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI '17), pp. 6706-6717, 2017.

국웅자연과학대학 수리과학부

  • 연구실/전공분야조합론, 대수적위상수학
  • 연구분야(AI 원천기술)Vision & Perception, Data Intelligence
  • 연구분야(X+AI)Medicine, Manufacturing

대표논문

Simplicial networks and effective resistance (co-author: K. Lee),
Advances in Applied Mathematics, Volume 100 (September 2018) 71-86
Can knowledge be more accessible in a virtual network?: Collective dynamics of knowledge transfer in a virtual knowledge organization network (coauthor: S. Shin),
Decision Support Systems (March 2014),
Combinatorial Green’s function of a graph and applications to networks,
Advances in Applied Mathematics, Volume 46 (Jan. 2011) 417-423
Topological data analysis can extract subgroups with high rates of Type 2 diabetes
(co-authors: H. Kim, C. Yi, Y. Kim, U. Park, B. Oh, H. Kim, T. Park),
International Journal of Data Mining and Bioinformatics 22(1):61-74 (20 April 2019 online)
Harmonic cycles for graphs, (co-author: Y. Kim)   
Linear and Multilinear Algebra (online February 2018)
위상수학적 조합론과 데이터 과학, 과학기술정보통신부, 2018-09-01 ~ 2022-08-31
심장질환판단서비스를 위한 딥러닝 알고리즘의 개발, 정보통신산업진흥원,
2019-09-01 ~ 2019-12-31

오성회공과대학 전기정보공학부

  • 연구실/전공분야로봇학습 연구실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Robotics & Action
  • 연구분야(X+AI)Manufacturing

대표논문

김건희공과대학 컴퓨터공학부

  • 연구실/전공분야시각 및 학습 연구실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Language & Cognition
  • 연구분야(X+AI)

대표논문

김아영공과대학 기계공학부

  • 연구실/전공분야로봇 인식 및 공간 지능 연구실
  • 연구분야(AI 원천기술)Vision & Perception,Autonomous Driving,Robotics & Action
  • 연구분야(X+AI)Manufacturing

대표논문

Giseop Kim, Sunwook Choi and Ayoung Kim, Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environments. IEEE Transactions on Robotics, 2021.
Joowan Kim, Younggun Cho and Ayoung Kim, Proactive Camera Attribute Control using Bayesian Optimization for Illumination-Resilient Visual Navigation. IEEE Transactions on Robotics, 36(4):1256-1271, 2020
Jinyong Jeong, Younggun Cho, Young-Sik Shin, Hyunchul Roh and Ayoung Kim, Complex Urban Dataset with Multi-level Sensors from Highly Diverse Urban Environments. International Journal of Robotics Research, 38(6):642-657, 2019.
  • 연구실/전공분야Molecular Electronics and Nanostructures Laboratory
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, AI Chip
  • 연구분야(X+AI)Brain, Energy

대표논문

주한별공과대학 컴퓨터공학부

  • 연구실/전공분야비주얼 컴퓨팅 연구실
  • 연구분야(AI 원천기술)Learning & Reasoning,Vision & Perception,Robotics & Action
  • 연구분야(X+AI)

대표논문

BANMo: Building Animatable 3D Neural Models from Many Casual Videos, CVPR 2022
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization.CVPR 2020
Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in A Triadic Interaction, CVPR 2019
Panoptic Studio: A Massively Multiview System for Social Interaction Capture, TPAMI 2019
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies, CVPR 2018

Myunghee Cho Paik (조명희)자연과학대학 통계학과

  • 연구실/전공분야생물통계 연구실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Data Intelligence
  • 연구분야(X+AI)Medicine, Commerce, Manufacturing

대표논문

Contextual multi-armed bandit algorithm for semiparametric reward model. presented at ICML 2019
Doubly Robust Lasso Bandit. presented at NeurIPs 2019
Principled analytic classifier for positive-unlabeled learning via weighted integral probability metric.  presented at ACML 2019 and published at Machine Learning
Lipschitz continuous autoencoders in application to anomaly detection.  accepted for AISTAT 2020
Uncertainty quantification using Bayesian neural networks in classification: Application to biomedical image segmentation. published at CSDA
딥러닝의 통계적 접근: 의료영상자료를 위한 합성곱 신경망 모형의 새로운 통계적 추론 방법 연구 (연구재단 중견연구, 2017-03-01 - 2020-02-29)

문태섭공과대학 전기정보공학부

  • 연구실/전공분야M.IN.D (Machine INtelligence and Data science) Lab
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Data Intelligence, Brain & Mind, AI Law & Ethics
  • 연구분야(X+AI)Brain, Bio, Energy

대표논문

Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization. Sangwon Jung, Taeeon Park, Sanghyuk Chun, and Taesup Moon. The 11th International Conference on Learning Representations (ICLR), May 2023

Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networks. Hongjoon Ahn, Youngyi Yang, Quan Gan, David Wipf, and Taesup Moon. Neural Information Processing Systems (NeurIPS), December 2022

GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training. Jaeseok Byun, Taebaek Hwang, Jianlong Fu, and Taesup Moon. European Conference on Computer Vision (ECCV), October 2022

Learning Fair Classifiers with Partially Annotated Group Labels. Sangwon Jung, Sanghyuk Chun, and Taesup Moon. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022

SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning. Sungmin Cha, Beomyoung Kim, Youngjoon Yoo, and Taesup Moon. Neural Information Processing Systems (NeurIPS), December 2021

SS-IL: Separated Softmax for Incremental Learning. Hongjoon Ahn, Jihwan Kwak, Subin Lim, Hyeonsu Bang, Hyojun Kim, and Taesup Moon. International Conference on Computer Vision (ICCV), October 2021

Fair Feature Distillation for Visual Recognition. Sangwon Jung, Donggyu Lee, Taeeon Park, and Taesup Moon. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021

FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noise. Jaeseok Byun, Sungmin Cha, and Taesup Moon. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021

Continual Learning with Node-Importance based Adaptive Group Sparse Regularization. Sangwon Jung, Hongjoon Ahn, Sungmin Cha, and Taesup Moon. Neural Information Processing Systems (NeurIPS), December 2020

Uncertainty-based continual learning with adaptive regularization. Hongjoon Ahn, Sungmin Cha, Donggyu Lee and Taesup Moon. Proceedings of Neural Information Processing Systems (NeurIPS), December 2019

Fooling neural network interpretations via adversarial model manipulation. Juyeon Heo, Sunghwan Joo, and Taesup Moon. Proceedings of Neural Information Processing Systems (NeurIPS), December 2019

곽노준융합과학기술대학원 지능정보융합학과

  • 연구실/전공분야컴퓨터지능 및 패턴인식 연구실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Multi-modal Learning
  • 연구분야(X+AI)

대표논문

Jisoo Jeong, Seungeui Lee, Jeesoo Kim and Nojun Kwak, "Consistency-based Semi-supervised Learning for Object detection", Thirty-third Conference on Neural Information Processing Systems (NeurIPS2019), Vancouver, Canada, Dec. 2019.
Simyung Chang, SeongUk Park, John Yang and Nojun Kwak, "Sym-Parameterized Dynamic Inference for Mixed-Domain Image Translation, International Conference on Computer Vision (ICCV2019), Seoul, Korea, Oct. 2019
Simyung Chang, John Yang, Jaeseok Choi and Nojun Kwak, "Genetic-Gated Networks for Deep Reinforcement Learning", Thirty-second Conference on Neural Information Processing Systems (NeurIPS2018), Montreal, Canada, Dec. 2018.
Jangho Kim, SeoungUK Park and Nojun Kwak, "Paraphrasing Complex Network: Network Compression via Factor Transfer", Thirty-second Conference on Neural Information Processing Systems (NeurIPS2018), Montreal, Canada, Dec. 2018.
Daesik Kim, Youngjoon Yoo, Jeesoo Kim, Sangkuk Lee and Nojun Kwak, "Dynamic Graph Generation Network: Generating Relational Knowledge from Diagrams", The Thirtieth IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2018), Salt Lake City, UT, June 2018.
Thinking Machine: 다중 감각간 관계 지식을 활용한 통합 사고 신경망 연구, 약 18억, 한국연구재단, 2017.11 - 2020.12

윤성로공과대학 전기정보공학부

  • 연구실/전공분야인공지능 연구실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Language & Cognition, AI Platform, AI Chip, Data Intelligence, AI Security
  • 연구분야(X+AI)Bio, Medicine, Pharma, Finance, Manufacturing, Energy

대표논문

한보형공과대학 전기정보공학부

  • 연구실/전공분야컴퓨터 비전 연구실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Language & Cognition
  • 연구분야(X+AI)

대표논문

Hyeonwoo Noh, Seunghoon Hong, Bohyung Han: Learning Deconvolution Network for Semantic Segmentation. ICCV 2015
Hyeonseob Nam, Bohyung Han: Learning multi-domain convolutional neural networks for visual tracking. CVPR 2016
Hyeonwoo Noh, Andre Araujo, Jack Sim, Tobias Weyand, Bohyung Han: Large scale image retrieval with attentive deep local features. ICCV 2017
Paul Hongseok Seo, Geeho Kim, Bohyung Han: Combinatorial Inference against Label Noise. NeurIPS 2019
Minsoo Kang, Jonghwan Mun, Bohyung Han: Towards Oracle Knowledge Distillation with Neural Architecture Search. AAAI 2020
Distributed Combinatorial Deep Learning. Google AI Focused Research Award
Privacy Preserving Semantic Image Compression. Kakao Brain
Neural Processing Research Center (대규모 인공 신경망에서의 학습 및 추론 알고리즘 개발), SAIT

현동훈자연과학대학 수리과학부

  • 연구실/전공분야대수기하학
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception
  • 연구분야(X+AI)Arts, Medicine

대표논문

오성주사회과학대학 심리학과

  • 연구실/전공분야심리학과 지각 실험실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Robotics & Action, Human-AI Interaction
  • 연구분야(X+AI)Bio, Arts, Humanities/Social Sciences, Brain

대표논문

Kwon, D., & Oh, S. (2019). The number of letters in number words influences the response time in numerical comparison tasks: Evidence using Korean number words. Attention, Perception, & Psychophysics, 81(8), 2612-2618.
Ryu, D., & Oh, S. (2018). The effect of good continuation on the contact order judgment of causal events. Journal of Vision, 18(11), 5-5.
Lee, H., & Oh, S. (2016). How directional change in reading/writing habits relates to directional change in displayed pictures. Laterality: Asymmetries of Body, Brain and Cognition, 21(1), 1-11.
Oh, S. (2013). Eyes can switch finger stroke. Perception, 42(6), 681–684.
Oh S. (2011). The eyeglass reversal. Attention, Perception & Psychophysics. 73, 1336-1343.
Baby mind: 아기 모사형 인공지능 개발
서울대학교 얼굴 데이터베이스 구축
미술감상에서 감상자 자세

이경무공과대학 전기정보공학부

  • 연구실/전공분야컴퓨터 비전 연구실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Autonomous Driving
  • 연구분야(X+AI)Bio, Medicine, Logistics, Manufacturing

대표논문

박창민의과대학 영상의학교실

  • 연구실/전공분야방사선인공지능연구실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Human-AI Interaction
  • 연구분야(X+AI)Medicine

대표논문

Development and Validation of a Deep Learning-Based Automated Detection Algorithm for Major Thoracic Diseases on Chest Radiographs. JAMA Netw Open. 2 (3), e191095 2019 Mar 1
Development and Validation of Deep Learning-based Automatic Detection Algorithm for Malignant Pulmonary Nodules on Chest Radiographs. Radiology. 290 (1), 218-228 Jan 2019
Development and Validation of a Deep Learning-based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs. Clin Infect Dis. 69 (5), 739-747 2019 Aug 16
Deep Learning for Chest Radiograph Diagnosis in the Emergency Department. Radiology. 293 (3), 573-580 Dec 2019
CT-based Deep Learning Model to Differentiate Invasive Pulmonary Adenocarcinomas Appearing as Subsolid Nodules Among Surgical Candidates: Comparison of the Diagnostic Performance With a Size-Based Logistic Model and Radiologists. Eur Radiol. 2020 Feb 13[Online ahead of print]
2017.03.-2020.02. 인공지능 딥러닝 알고리즘을 이용한 폐결절 분류 및 폐암 진단 시스템 개발. 한국연구재단 (미래창조과학부)
2017.11-2019.10.31. 다기관 의료영상 인공지능 연구를 위한 보안 클라우드 플랫폼. 서울시 산학연 협력사업 (서울시)

엄문영사범대학 교육학과

  • 연구실/전공분야교육조직론, 학교개혁, 교사교육, 교육기획 및 재정
  • 연구분야(AI 원천기술)Vision & Perception, Human-AI Interaction, AI Law & Ethics
  • 연구분야(X+AI)Humanities/Social Sciences, Finance

대표논문

정의철서울대학교병원 보라매

  • 연구실/전공분야성형외과
  • 연구분야(AI 원천기술)Vision & Perception,Robotics & Action
  • 연구분야(X+AI)Medicine

대표논문

서종모공과대학 전기정보공학부

  • 연구실/전공분야전기-의학 융합연구실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception, Robotics & Action, Human-AI Interaction, Data Intelligence, AI Law & Ethics, Autonomous Driving
  • 연구분야(X+AI)Bio, Brain, Medicine

대표논문

예성준융합과학기술대학원 응용바이오공학과

  • 연구실/전공분야방사선의학물리연구실
  • 연구분야(AI 원천기술)Vision & Perception
  • 연구분야(X+AI)Bio, Medicine

대표논문

정천기자연과학대학 뇌인지과학과

  • 연구실/전공분야인간 뇌 기능 연구실
  • 연구분야(AI 원천기술)Vision & Perception, Robotics & Action, Human-AI Interaction
  • 연구분야(X+AI)Bio, Brain, Medicine

대표논문

Characterization of brain network supporting episodic memory in the absence of one medial temporal lobe.

Jeong W, Lee H, Kim JS, Chung CK.

Hum Brain Mapp. 2019 May;40(7):2188-2199.
Direct Stimulation of Human Hippocampus During Verbal Associative Encoding Enhances Subsequent Memory Recollection.

Jun S, Kim JS, Chung CK.

Front Hum Neurosci. 2019 Feb 5;13:23.
Neural basis of episodic memory in the intermediate term after medial temporal lobe resection.

Jeong W, Lee H, Kim JS, Chung CK.

J Neurosurg. 2018 Oct 26;131(3):790-798.
Postoperative seizure outcome-guided machine learning for interictal electrocorticography in neocortical epilepsy.

Park SC, Chung CK.

J Neurophysiol. 2018 Jun 1;119(6):2265-2275.
Disrupted Resting State Network of Fibromyalgia in Theta frequency.

Choe MK, Lim M, Kim JS, Lee DS, Chung CK.

Sci Rep. 2018 Feb 1;8(1):2064.
감각운동통합 상지 제어 뇌-컴퓨터 인터페이스 개발, 연구재단, 2016-2020
작업기억의 기전, 연구재단, 2018-2020

최진영공과대학 전기정보공학부

  • 연구실/전공분야인지지능 연구실
  • 연구분야(AI 원천기술)Learning & Reasoning, Vision & Perception
  • 연구분야(X+AI)security, visual surveillance

대표논문

Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning, CVPR 2017
A Comprehensive Overhaul of Feature Distillation, ICCV 2019
Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning, ICCV 2019
Associative Variational Auto-encoder with Distributed Latent Spaces and Associators, AAAI 2020
Context-aware Deep Feature Compression for High-speed Visual Tracking, CVPR 2018
예지형 시각 지능 원천 기술 개발, 과학기술정보통신부, 2014.  4.  1 ~ 2024.  2. 29
Thinking Machine: 다중 감각 심층 신경망 기반 연상 작용의 실현 및 영상 생성 연구, 과학기술정보통신부, 2017. 09. 01 - 2020. 12. 31
실외 무인 경비 로봇을 위한 멀티모달 지능형 정보분석 기술 개발, 과학기술정보통신부, 2017. 04. 01 ~ 2021. 12. 31