SEUNGRYUL BAEK (SB)


Contact

E-mail : s.baek15@imperial.ac.uk // sryul.baek@gmail.com (personal)
Dept. of Electrical and Electronic Engineering (EEE), 
Imperial College London, London, SW7 2BT, UK

I'm currently holding the UK Tier-4 Student VISA.

Research Interest
  • Computer Vision and Machine Learning (Deep Learning).
  • Hand Pose Estimation, Action/Gesture recognition, Semantic segmentation, Object recognition.
Education
Work Experience
  • Computer Vision EngineerSamsung Electronics, DMC Research, Suwon, South Korea.
    • This job is taken as the alternative to the military duties in South Korea.
    • Feb. 2011~Feb.2015.
Publication
  • Seungryul Baek, Kwang In Kim, Tae-Kyun Kim, "Augmented skeleton space transfer for depth-based hand pose estimation", in CVPR 2018 (Oral presentation, 2.1% Accept ratio). [Link]

  • Guillermo Garcia-Hernando, Shanxin Yuan, Seungryul Baek, Tae-Kyun Kim, "First-person hand action benchmark with RGB-D videos and 3D hand pose annotations", in CVPR 2018. [Link]

  • Seungryul Baek, Zhiyuan Shi, Masato Kawade, Tae-Kyun Kim, "Kinematic-layout-aware random forests for depth-based action recognition", in BMVC 2017 (Oral presentation, 5.6% Accept ratio). [PDF] [SUP]
  • Seungryul Baek, Kwang In Kim, Tae-Kyun Kim, "Real-time online action detection forests using spatio-temporal contexts", in WACV 2017. [PDF]

  • Seungryul Baek, Taegyu Lim, Yong Seok Heo, Sungbum Park, Hantak Kwak and Woosung Shim, "Superpixel coherency and uncertainty models for semantic segmentation", in ICCV Workshop 2013. [PDF]

  • Seungryul Baek, Chang D. Yoo, Sungrack Yun, "Learning a discriminative visual codebook using homonym scheme", in ICASSP 2011. [PDF]
Awards
  • Finalist at Qualcomm Innovation Fellowship 2018.
  • Silver prize at Samsung Best Paper Awards 2013. 
Academic Activities
  • Challenge Commitee at ECCV 2018 HANDS Workshop.
  • Reviewer at IJCV 2018.
  • Student Volunteer at BMVC 2017.