SeongTaeKim

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

Dr. Seong Tae Kim

  • Assistant Professor

  • Email: st.kim [@] khu.ac.kr

Short Curriculum Vitae

2019-2021 Postdoctoral Research Associate, CAMP - Technische Universität München (TUM), Munich, Germany
2014-2019 Ph.D. Electrical Engineering,Image and Video Systems Laboratory, KAIST(Korea Advanced Institute of Science and Technology), South Korea
under the supervision of Prof. Dr. Yong Man Ro
2015 Visiting Researcher in Department of Electrical and Computer Engineering, University of Toronto, Canada
under the supervision of Prof. Dr. Konstantinos N. Plataniotis
2012-2014 M.S. Electrical Engineering,Image and Video Systems Laboratory, KAIST(Korea Advanced Institute of Science and Technology), South Korea
under the supervision of Prof. Dr. Yong Man Ro
2008-2012 B.S. Electrical Engineering, Korea University, South Korea

Research Interests

  • Deep Learning for Medical Image Analysis
  • Spatio-temporal Learning/ Longitudinal Data Analysis
  • Explainable/Interpretable Deep Learning
  • Computer-aided Diagnosis
  • Surgical Workflow Analysis

Awards & Honors

  • Selected Project for Research Credit (6K USD) at Google Cloud, 2020
  • Outstanding Reviewer Award at British Machine Vision Conference (BMVC) 2020
  • Selected Project for Research Credit (5K USD) at Google Cloud, 2019
  • Robert F. Wagner All-Conference Best Student Paper Award at SPIE Medical Imaging 2018, Houston, USA
  • Best 10% Paper Award, at IEEE International Conference on Image Processing 2015, Quebec City, Canada
  • Honorable Mentioned Poster Award, at SPIE Medical Imaging 2015, Orlando, USA
  • Research Excellence Award at School of Electrical Engineering, KAIST (2015-2017)
  • 24th Samsung_HumanTech Honorable mentions at Samsung Electronics, 2018
  • 23rd Samsung_HumanTech Paper Award at Samsung Electronics, 2017
  • Best Paper Award, at Korea Multimedia Society (2012, 2016)
  • Semester High Honor, at Korea University (2008, 2011)

Professional Services

  • Reviewer for ICCV 2021
  • Reviewer for MICCAI 2021
  • Program Committee Member at AAAI 2021
  • Reviewer for ECCV 2020
  • Reviewer for MICCAI 2020
  • Reviewer for BMVC 2020
  • Reviewer for IROS 2020
  • Program Committee Member at International Conference on Multimedia Modeling 2020
  • Reviewer for MICCAI 2019
  • Reviewer for IEEE Transactions on Medical Imaging
  • Reviewer for IEEE Transactions on Cybernetics
  • Reviewer for IEEE Transactions on Image Processing
  • Reviewer for IEEE Transactions on Multimedia
  • Reviewer for IEEE Transactions on Circuits Systems and Video Technology
  • Reviewer for Neurocomputing
  • Reviewer for Computers in Biology and Medicine
  • Reviewer for Computational and Structural Biotechnology Journal
  • Reviewer for Computer Methods and Programs in Biomedicine
  • Reviewer for Digital Signal Processing
  • Session chair at IEEE International Conference on Image Processing 2015 (Computer-assisted Screening and Diagnosis session)

Open Positions (Internship of graduate students)

I am always looking for strong graduate students to collaborate with. If you are coming with third-party funding and interested in our research topics, then please feel free to contact me by email.

Available

Running
Master ThesisSurgical Workflow Analysis under Limited Annotation
(Dr. Seong Tae Kim, Tobias Czempiel, Prof. Dr. Nassir Navab)
Master ThesisInteractive Segmentation for Improving Infection Quantification in CT scans
(Dr. Seong Tae Kim, Prof. Dr. Nassir Navab)
Master ThesisGradient Surgery for Multitask Longitudinal CT Analysis
(Dr. Seong Tae Kim, Prof. Dr. Nassir Navab)
Master ThesisTowards Human-Like Predictor with Rejection Option
(Dr. Seong Tae Kim, Prof. Dr. Nassir Navab)
Master ThesisEvaluating Human Skills using Deep Neural Networks
(Dr. Seong Tae Kim, Prof. Dr. Nassir Navab)
Master ThesisSemi-supervised Active Learning
(Dr. Seong Tae Kim, Prof. Dr. Nassir Navab)

Finished
Master ThesisDeep Generative Model for Longitudinal Analysis
(Dr. Seong Tae Kim, Prof. Dr. Nassir Navab)
Master ThesisRobust training of neural networks under noisy labels
(Dr. Seong Tae Kim, Dr. Shadi Albarqouni, Prof. Dr. Nassir Navab)
ProjectInvestigation of Interpretation Methods for Understanding Deep Neural Networks
(Dr. Seong Tae Kim, Prof. Dr. Nassir Navab)
Master ThesisDisentangled Representation Learning of Medical Brain Images using Flow-based Models
(Dr. Seong Tae Kim, Matthias Keicher, Prof. Dr. Nassir Navab)
Master ThesisSelf-supervised learning for out-of-distribution detection in medical applications
(Dr. Seong Tae Kim, Prof. Dr. Nassir Navab)
Master ThesisLearning to learn: Which data we have to annotate first in medical applications?
(Dr. Seong Tae Kim, Prof. Dr. Nassir Navab)
IDPMultiple sclerosis lesion segmentation from Longitudinal brain MRI
(Dr. Seong Tae Kim, Ashkan Khakzar, Prof. Dr. Nassir Navab)
Master ThesisDevelopment of spatio-temporal segmentation model for tumor volume calculation in micro-CT
(Dr. Shadi Albarqouni, Dr. Seong Tae Kim, Dr. Guillaume Landry, Prof. Dr. Nassir Navab)
Master ThesisContinual and incremental learning with less forgetting strategy
(Dr. Seong Tae Kim, Prof. Dr. Nassir Navab)
ProjectHandling Imbalanced Data Problem in Chest X-ray Multi-label Classification
(Dr. Seong Tae Kim, Ashkan Khakzar, Prof. Dr. Nassir Navab)
ProjectUnderstanding Medical Images to Generate Reliable Medical Report
(Dr. Shadi Albarqouni, Dr. Seong Tae Kim, Prof. Dr. Nassir Navab)

Publications

2020
A. Ravi, S.T. Kim, F. Pfister, F. Pfister, N. Navab
Self-supervised out-of-distribution detection in brain CT scans
The first two authors contributed equally.
Medical Imaging meets NeurIPS? workshop
(bib)
M. Tirindelli, M. Victorova, J. Esteban, S.T. Kim, D. Navarro-Alarcon, Y.P. Zheng, N. Navab
Force Ultrasound Fusion: Bringing Spine Robotic-US to the Next "Level"
IEEE Robotics and Automation Letters (presented at IROS2020) (bib)
S. Denner, A. Khakzar, M. Sajid, M. Saleh, Z. Spiclin, S.T. Kim, N. Navab
Spatio-temporal learning from longitudinal data for multiple sclerosis lesion segmentation
The first two authors contributed equally.
BrainLes? at International Conference on Medical Image Computing and Computer-Assisted Intervention.
(bib)
T. Czempiel, M. Paschali, M. Keicher, W. Simson, H. Feußner, S.T. Kim, N. Navab
TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks
International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI), Lima, Peru, 2020 (The pre-print is available currently online on arXiv) (bib)
H. Lee, H. Lee, S.T. Kim, Y.M. Ro
Robust Ensemble Model Training via Random Layer Sampling Against Adversarial Attack
31st British Machine Vision Virtual Conference (BMVC) (bib)
L.C.O. Tiong, S.T. Kim, Y.M. Ro
Multimodal facial biometrics recognition: Dual-stream convolutional neural networks with multi-feature fusion layers
Image and Vision Computing (bib)
H. Lee, S.T. Kim, H. Lee, N. Navab, Y.M. Ro
Efficient Ensemble Model Generation for Uncertainty Estimation with Bayesian Approximation in Segmentation
The first two authors contributed equally.
arXivPreprint:2005.10754
(bib)
J.U. Kim, S.T. Kim, E.S. Kim, S.K. Moon, Y.M. Ro
Towards High-performance Objective Detection: Task-specific Design Considering Classification and Localization Separation
45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2020. (bib)
S.T. Kim, F. Mustaq, N. Navab
Confident Coreset for Active Learning in Medical Image Analysis
The first two authors contributed equally.
arXiv:2004.02200.
(bib)
2019
A. Khakzar, S. Baselizadeh, S. Khanduja, S.T. Kim, N. Navab
Explaining Neural Networks via Perturbing Important Learned Features
pre-print version is available online at arXiv (bib)
H. Lee, S.T. Kim, J.Lee, Y.M. Ro
Realistic Breast Mass Generation through BIRADS Category
22nd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Shenzhen, China, 2019 (bib)
H. Lee, S.T. Kim, Y.M. Ro
Generation of Multimodal Justification Using Visual Word Constraint Model for Explainable Computer-Aided Diagnosis
MICCAI Workshop on Interpretability of Machine Intelligence in Medical Image Computing, Shenzhen, China, 2019 (bib)
H. Lee, S.T. Kim, Y.M. Ro
Building a Breast-Sentence Dataset: Its Usefulness for Computer-Aided Diagnosis
International Conference on Computer Vision (ICCV) Workshops, Seoul, Korea, 2019 (bib)

Selected publications

You can find full publication records (2014~2019) here.

* S.T. Kim, Y.M. Ro. Attended relation feature representation of facial dynamics for facial authentication. IEEE Transactions on Information Forensics and Security 2019.

* H.J. Lee, S.T. Kim, H. Lee, Y.M. Ro. Lightweight and effective facial landmark detection using adversarial learning with face geometric map generative network. IEEE Transactions on Circuits and Systems for Video Technology 2019.

* S.T. Kim, Y.M. Ro. Facial dynamics interpreter network: What are the important relations between local dynamics for facial trait estimation?. European Conference on Computer Vision(ECCV), Munich, Germany, 2018.

* J. Lee, S.T. Kim, H. Lee, Y.M. Ro. Feature2Mass: Visual feature processing in latent space for realistic labeled mass generation. European Conference on Computer Vision Workshop, Munich, Germany, 2018.

* S.T. Kim, H.M. Lee, J.H. Lee, Y.M. Ro. Visually interpretable deep network for diagnosis of breast masses on mammograms. Physics in Medicine and Biology, 2018.

* S.T. Kim, H. Lee, H.G. Kim, Y.M. Ro. ICADx: Interpretable computer-aided diagnosis of breast masses. SPIE Medical Imaging, USA (Robert F. Wagner All Conference Best Student Paper Final Lists Award), 2018.

* D.H. Kim, S.T. Kim, J.M. Chang, Y.M. Ro. Latent feature representation with depth directional long-term recurrent learning for breast masses in digital breast tomosynthesis. Physics in Medicine and Biology, 2017.

* S.T. Kim, D.H. Kim, Y.M. Ro. Detection of masses in digital breast tomosynthesis using complementary information of simulated projection. Medical Physics 2015.

* D.H. Kim, S.T. Kim, Y.M. Ro. Improving mass detection using combined feature representations from projection views and reconstructed volume of DBT and boosting based classification with feature selection. Physics in Medicine and Biology, 2015.

* D.H. Kim, S.T. Kim, Y.M. Ro. Feature extraction from bilateral dissimilarity in digital breast tomosynthesis reconstructed volume. IEEE International Conference on Image Processing, Quebec City, Canada (Best 10% paper), 2015.

* D.H. Kim, S.T. Kim, Y.M. Ro. Feature extraction from inter-view similarity of DBT projection views. SPIE Medical Imaging, Orlando, USA (Honorable Mentioned Poster Award), 2015.

* S.T. Kim, D.H. Kim, Y.M. Ro. Breast mass detection using slice conspicuity in 3D reconstructed digital breast volumes. Physics in Medicine and Biology, 2014.

Teaching



Edit | Attach | Refresh | Diffs | More | Revision r1.7 - 06 Apr 2021 - 14:16 - SeongTaeKim

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif