Seil Na

Hello! I am a Master student in Computer Science Engineering at Seoul National University. My advisor is Gunhee Kim. Previously, I was a research intern in Kakao Brain.

My research is on Computer Vision, Natural Language Processing and Machine Learning, particularly Story Understanding and Interpretable AI systems.

Email  /  CV  /  Google Scholar

Research
Encoding Video and Label Priors for Multi-label Video Classification on YouTube-8M dataset
Seil Na, Younjae Yu, Sangho Lee, Jisung Kim, Gunhee Kim
CVPR Workshop on YouTube-8M Large-Scale Video Understanding, 2017
arXiv / bibtex / code

We propose a deep neural network model, which consists of four components: the frame encoder, the classification layer, the label processing layer, and the loss function. We ranked 8th out of 655 teams in Google Cloud & YouTube-8M Video Understanding Challenge.

A Read-Write Memory Network for Movie Story Understanding
Seil Na, Sangho Lee, Jisung Kim, Gunhee Kim
ICCV, 2017
arXiv / bibtex / code

We propose a novel memory network model named Read-Write Memory Network (RWMN) to perform question and answering tasks for large-scale, multimodal movie story understanding.