Hoya012's Research Blog

About Ho Seong Lee

  • Hoseong Lee received the B.S. degrees, in Electrical and Computer Engineering from Seoul National University, Seoul, Korea, in 2016.
  • Hoseong Lee received the M.S. degrees, in Electrical and Computer Engineering from Seoul National University, Seoul, Korea, in 2018.
  • In 2018, he joined the SUALAB.,Seoul, Korea, as a Machine Learning Engineer.
  • His research interests include algorithm and architecture for image recognition, image processing using deep learning.
  • Repository

  • https://github.com/hoya012/CVPR-2019-Paper-Statistics
  • https://github.com/hoya012/deep_learning_object_detection
  • https://github.com/hoya012/awesome-anomaly-detection
  • https://github.com/hoya012/fast-style-transfer-tutorial-pytorch
  • https://github.com/hoya012/shake-shake-tensorflow
  • https://github.com/hoya012/pytorch-densenet
  • https://github.com/hoya012/pytorch-peleenet
  • https://github.com/hoya012/pytorch-Xception
  • https://github.com/hoya012/pytorch-MobileNet
  • https://github.com/hoya012/pytorch-partial-conv-based-padding
  • Slides

  • "Single Image Super Resolution Overview"
  • "2019 ICLR Best Paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" Review"
  • "2019 CVPR Paper Statistics & Paper Review"
  • "Pelee: a real time object detection system on mobile devices, 2018 NeurIPS" Paper Review
  • "How does batch normalization help optimization, 2018 NeurIPS" Paper Review
  • "Simple Does It: weakly supervised instance and semantic segmentation, 2017 CVPR" Paper Review
  • "From image level to pixel-level labeling with convolutional networks, 2015 CVPR" Paper Review
  • "Dataset and metrics for predicting local visible differences, 2018 SIGGRAPH" Paper Review
  • "Learning From Noisy Large-Scale Datasets With Minimal Supervision, 2017 CVPR" Paper Review
  • "Learning transferable architectures for scalable image recognition, 2018 CVPR" Paper Review
  • "Searching for Activation Functions, 2018 ICLR" Paper Review
  • "Google Vizier: A Service for Black-Box Optimization, 2017 KDD" Paper Review
  • Teaching Experience

  • Lecturer of Object Detection Workshop, in FastCampus, 2018.10 ~ 2019.5
  • TA of Digital System Design and Experiments(디지털 시스템 설계 및 실습) , in SNUECE(서울대학교 전기정보공학부), 2017.9 ~ 2017.12
  • TA of Digital System Design and Experiments(디지털 시스템 설계 및 실습) , in SNUECE(서울대학교 전기정보공학부), 2016.9 ~ 2016.12
  • Publications

  • Donghyeon Lee, Sangheon Lee, Ho Seong Lee, Kyujoong Lee, and Hyuk-Jae Lee, “Context-Preserving Filter Reorganization for VDSR-Based Super-resolution," IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), Mar. 2019.
  • 이호성, "CNN 및 Edge detection 기반 고속 손 동작 인식", 서울대학교 전기정보공학부 석사학위논문(Thesis), Feb. 2018
  • Ho Seong Lee, Donghyeon Lee, Jinsung Kim, and Hyuk-Jae Lee, "Fast Hand Gesture Recognition with CNN and Feature Matching", 30th Workshop on Image Processing and Image Understanding, Feb. 2018 (Best Paper)
  • 이호성, 이동현, 김진성, 이혁재, “임베디드 보드 환경에서의 효율적인 손 인식 및 추적 방법에 대한 연구”, 제25회 한국반도체학술대회, Feb. 2018
  • Donghyeon Lee, Ho Seong Lee, Kyujoong Lee, and Hyuk-Jae Lee, "Super-Resolution을 위한 Deconvolution 적용 고속 컨볼루션 뉴럴 네트워크," 한국멀티미디어학회 논문지, Volume: 20, Issue: 11, Pages: 1750-1758, Nov. 2017.
  • 이호성, 이동현, 이규중, 이혁재, “CNN 알고리즘의 하드웨어 구현을 위한 고정 소수점 모델 구현 및 성능 분석,” 2017년도 대한전자공학회 하계종합학술대회, June. 2017
  • Donghyeon Lee, Ho Seong Lee, Hyun Kim, Jin-Sung Kim, and Hyuk-Jae Lee, “An Evenly Distributed Points based Hand Tracking Method,” International Technical Conference on Circuits/Systems, Computers and Communications, July. 2017
  • 이호성, 이동현, 김진성, 이혁재, "Markov Model 기반 손 제스처 인식 알고리즘", SoC 학술대회, May, 2017
  • Contact Me

    If you have questions about the post, feel free to email me or create an issue on GitHub. Enjoy!