Embedded Files
Jisung Kim
Research Engineer
Vision begins with the detection of light from the world. (in Learning OpenCV at 370 page)
Computer Vision > Multimodal LLM > Vision Language Action Model
2003 ~ 2008 B.S. @ KAIST EECS
2008 ~ 2010 M.S. @ KAIST Robotics Research Lab
2010 ~ 2015 Samsung Techwin (Technology Winner in digital world.)
2015 ~ SK Telecom Multimodal Application Team
runhani [at] gmail.com
Research Interests
Multimodal Large Language Model, Video Multi Label Classification, Optical Character Recognition, Image Captioning, Face Recognition, Vision Language Model (VLM), Vision Language Action (VLA), Physical AI
NUGU Nemo
Hand Posture Recognition for Kids Game (손동작 인식 엔진 개발)
FRVT 1:1
Face Recognition Vendor Test 국내 1위, 세계 12위 at VISABORDER Photos FNMR@FMR <1e-6 (21.07.09)
Sullivan +
Image Captioning, Face Recognition, Gender/Age Prediction
Kaggle
The 1st Youtube-8M Video Understanding Challenge (2017)
: Ranked at 8th / 650 teams (Team Gold Medal)
The 2nd Youtube-8M Video Understanding Challenge (2018)
: Ranked at 43th / 394 teams (Solo Silver Medal in a week)
The 3rd Youtube-8M Video Understanding Challenge (2019)
: Ranked at 19th / 283 teams (Team Silver Medal)
Kaggle Competitions Master
Patent
영상 안정화 방법 및 장치 Method and Apparatus for Stabilizing Video (등록번호 : 1019452330000)
차량 감시 시스템 Vehicle Monitoring System (등록번호 : 1017679220000)
Publication
International Conference
Discriminative Common Vectors in DCT domain For Face Recognition
Jisung Kim, Kwang Ho An, Won Hwa Kim, and Myung Jin Jung
The 6th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Nov 2009.
Encoding Video and Label Priors for Multi-label Video Classification on YouTube-8M dataset
Seil Na, YoungJae Yu, Sangho Lee, Jisung Kim, Gunhee Kim
Workshop on Youtube-8M Large-Scale Video Understanding (CVPR Workshop 2017)
A Read-Write Memory Network for Movie Story Understanding
Seil Na, Sangho Lee, Jisung Kim, Gunhee Kim
International Conference on Computer Vision (ICCV), Oct 2017.
International Journal
Robust Video Stabilization Using Particle Keypoint Update and l1-Optimized Camera Path
Semi Jeon, Inhye Yoon, Jinbeum Jang, Seungji Yang, Jisung Kim, and Joonki Paik
IEEE Sensors Journal, 2017.
Domestic Journal
로봇 사진사를 위한 오메가 형상 추적기와 얼굴 검출기 융합을 이용한 강인한 머리 추적
김지성, 정지훈, 안광호, 유연걸, 이원형
Journal of Korea Robotics Society, 2010.
Google Sites
Report abuse