Career Profile

I’m research scientist at Twelve Labs.

Curriculum Vitae(PDF).

Education

Seoul National University, Seoul, Korea.

2019.03 - 2021.02

Seoul National University, Seoul, Korea.

2012.03 - 2018.02

Experiences

ML Research Scientist

2023.06 - Current
Twelve labs, Seoul, Korea.
  • Video search

Machine Learning Engineer

2021.10 - 2023.06
IPX (Line Friends), Seoul, Korea.
  • Frenz dev

Research Scientist

2021.03 - 2021.09
Violet, Seoul, Korea.
  • Work on automated video magazine editing.
  • Including video classification, magazine layout recommendation and text generation.

Graduate Researcher

2019.03 - 2021.02
Vision and Learning Lab, Seoul, Korea.
  • Worked on video captioning and character re-identification.
  • Worked on interactive image retrieval and change captioning.

Research Intern

2018.03 - 2019.02
Kakao Brain, Sungnam, Korea.
  • Worked on text-to-speech algorithm, speaker adaptation and encoding.
  • Worked on web video classification, visual question answering.

Undergraduate Researcher

2017.06 - 2018.02
Vision and Learning Lab, Seoul, Korea.
  • Worked on movie video captioning, language based retrieval algorithm

Publications

Viewpoint-Agnostic Change Captioning with Cycle Consistency

Hoeseong Kim, Jongseok Kim, Hyungseok Lee, Hyunsung Park, Gunhee Kim

ICCV 2021

Transitional Adaptation of Pretrained Models for Visual Storytelling

Youngjae Yu, Jiwan Chung, Heeseung Yun, Jongseok Kim, Gunhee Kim

CVPR 2021

Jongseok Kim, Youngjae Yu, Hoeseong Kim, Gunhee Kim

AAAI 2021

Youngjae Yu, Jongseok Kim, Heeseung Yun, Jiwan Chung, Gunhee Kim

ECCV 2020 spotlight

Youngjae Yu, Jongseok Kim, Gunhee Kim

ECCV 2018

Workshops

Cycled Compositional Learning between Images and Text

Jongseok Kim, Youngjae Yu, Seunghwan Lee, Gunhee Kim

CVPR 2020, Third Workshop on Computer Vision for Fashion, Art and Design

Temporal Attention Mechanism with Conditional Inference for Large-Scale Multi-Label Video Classification

Eun-Sol Kim, Kyoung-Woon On, Jongseok Kim, Yu-Jung Heo, Seong-Ho Choi, Hyun-Dong Lee, Byoung-Tak Zhang

ECCV 2018, Second Workshop on Youtube-8M Large-Scale Video Understanding

awards