TAE SOO KIM

profile_pic

Department of Computer Science

Johns Hopkins University

tkim60-at-jhu-dot-edu

Curriculum Vitae

ABOUT ME

I am a 4th year PhD candidate in the Department of Computer Science at Johns Hopkins. I am advised by Prof. Gregory Hager and I work closely with with Prof. Austin Reiter and Prof. Alan Yuille . I am a member of the Computational Interaction and Robotics Laboratory . My recent work focuses on computer vision methods for structured learning of compositional representation from video data. I am also interested in using synthetic data to learn complex visual tasks. I work towards applying such models to activity recognition, skill assessment in surgery and robotics.


I received both my B.S and M.S.E degrees from the Department of Computer Science at The Johns Hopkins University. Under the supervision of Prof. Russell Taylor and Prof. Austin Reiter , I worked on building real-time 3D reconstruction systems for laparoscopic endoscopic surgery. I am originally from Seoul, am a big fan of Arsenal and love playing baseball. I also serve as a president of the Korean Graduate Student Association at JHU.

PUBLICATIONS

Crowdsourcing annotation of surgical instruments in videos of cataract surgery
Tae Soo Kim , Anand Malpani, Austin Reiter, Gregory D. Hager, Shameema Sikder, S. Swaroop Vedula
MICCAI 2018: LABELS Workshop


Train, Diagnose and Fix: Interpretable Approach for Fine-grained Action Recognition
Tae Soo Kim* , Jingxuan Hou*, Austin Reiter
arxiv 2018


Interpretable 3D Human Action Analysis with Temporal Convolutional Networks
Tae Soo Kim , Austin Reiter
CVPR 2017: BNMW Workshop
Oral Presentation


Bone Removal in CT Angiography Using Deep Image-to-Image Network with Transfer and Multi-Task Learning
Mingqing Chen, Tae Soo Kim , Shaohua Zhou, Max Schoebinger, Daguang Xu, Zhoubing Xu, Dong Yang, Yefeng Zheng, Dorin Comaniciu
In submission to MICCAI 2017

COLLABORATIONS

  1. Kim TK, Yi PH, Wei J, Shin J, Barnoy Y, Kim T, Hager GD, Sair H, Lin C, Hui FK, Fritz J. Deep Learning for Detection of Hip, Knee, and Shoulder Arthroplasty Dislocations and Transfer Learning to Native Joint Dislocations. Scientific Discovery Theater Poster & Oral Presentation, Radiological Society of North America 103rd Scientific Assembly and Annual Meeting, Chicago, IL.
  2. Yi PH, Kim TK, Wei J, Shin J, Kim T, Hager GD, Harvey S, Sair H, Hui FK, Lin C. Identification of Pneumoperitoneum on Chest Radiographs Using Deep Learning. Podium presentation, Radiological Society of North America 103rd Scientific Assembly and Annual Meeting, Chicago, IL
  3. Kim TK, Yi PH, Shin J, Wei J, Kim T, Hager GD, Sair H, Hui FK, Lin C. PedsCheXNet: Deep Learning-Based Automated Detection of Pediatric Thoracic Diseases. Podium presentation, Radiological Society of North America 103rd Scientific Assembly and Annual Meeting, Chicago, IL
  4. Yi PH, Kim TK, Wei J, Shin J, Kim T., Hager GD, Sair H, Hui FK, Lin C. Radiology “Forensics”: Determination of Age and Gender from Chest X-Rays Using Deep Learning. Podium presentation, Radiological Society of North America 103rd Scientific Assembly and Annual Meeting, Chicago, IL.
  5. Yi PH, Kim TK, Wei J, Shin J, Kim T, Hager GD, Lin C, Sair H, Hui FK, Fritz J. Semantic Labeling of Pediatric Musculoskeletal Radiographs Using Deep Learning. Podium presentation, Radiological Society of North America 103rd Scientific Assembly and Annual Meeting, Chicago, IL
  6. Kim TK, Yi PH, Kim T, Hager GD, Lin C. Development and Visual Assessment of a Deep Learning System for Automated Tuberculosis Screening Using Chest Radiographs. Poster Presentation (RSNA R&E Grant AI/ML Highlight) Radiological Society of North America 103rd Scientific Assembly and Annual Meeting, Chicago, IL.

PRESENTATIONS

TEACHING

  • Head Teaching Assistant for EN.600.661, Computer Vision.
    This course exposes students to fundamental methods in computer vision from a computational perspective. Topics studied include: camera modeling, computation of 3D geometry from stereo, motion, photometric stereo, object recognition to modern deep learning. Fall 2015,2016

  • Head Teaching Assistant for EN.600.684, Augmented Reality.
    In this course, students learn about mathematical methods used for calibration, tracking, multi-modal registration, advance visualization and medical augmented reality applications. Spring 2016

  • Head Teaching Assistant for EN.600.107, Introductory Programming in Java.
    This course introduces fundamental structured and object-oriented programming concepts and techniques using Java. Summer 2015

  • Head Teaching Assistant for EN.600.226, Data Structures.
    This course covers the design and implementation of data structures including arrays, stacks, queues, linked lists, binary trees, heaps, balanced trees and graphs. Spring 2015