Ahjeong Seo — accepted AI-conference papers

2021

Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering

Ahjeong Seo, Gi-Cheon Kang, Joonhan Park, Byoung-Tak Zhang

ACL 2021long

Video Question Answering is a task which requires an AI agent to answer questions grounded in video. This task entails three key challenges: (1) understand the intention of various questions, (2) capturing various elements of the input video (e.g., object, action, causality), and (3) cross-modal gro…

Cited by 72 Source ↗PDF ↗code ↗Scholar ↗

2021

DramaQA: Character-Centered Video Story Understanding with Hierarchical QA

Seongho Choi, Kyoung-Woon On, Yu-Jung Heo, Ahjeong Seo, Youwon Jang, Minsu Lee +1

AAAI 2021technical

Despite recent progress on computer vision and natural language processing, developing a machine that can understand video story is still hard to achieve due to the intrinsic difficulty of video story. Moreover, researches on how to evaluate the degree of video understanding based on human cognitive…

Cited by 67 Source ↗PDF ↗code ↗Scholar ↗