메뉴 건너뛰기
Library Notice
Institutional Access
If you certify, you can access the articles for free.
Check out your institutions.
ex)Hankuk University, Nuri Motors
Log in Register Help KOR
Subject

DramaQA: Character-Centered Video Story Understanding with Hierarchical QA
Recommendations
Search
Questions

DramaQA: 계층적 질의응답과 함께하는 등장인물 중심 비디오 스토리 이해

논문 기본 정보

Type
Academic journal
Author
Seongho Choi (서울대학교) Kyoung-Woon On (Kakao Brain) Yu-Jung Heo (서울대학교) Youwon Jang (서울대학교) Ahjeong Seo (서울대학교) Seungchan Lee (서울대학교) Minsu Lee (서울대학교) Byoung-Tak Zhang (서울대학교)
Journal
Korean Institute of Information Scientists and Engineers KIISE Transactions on Computing Practices Vol.27 No.1 KCI Accredited Journals
Published
2021.1
Pages
1 - 7 (7page)
DOI
10.5626/KTCP.2021.27.1.7

Usage

cover
📌
Topic
📖
Background
🔬
Method
🏆
Result
DramaQA: Character-Centered Video Story Understanding with Hierarchical QA
Ask AI
Recommendations
Search
Questions

Research history (3)

  • Are you curious about the follow-up research of this article?
  • You can check more advanced research results through related academic papers or academic presentations.
  • Check the research history of this article

Abstract· Keywords

Report Errors
In this paper, we propose a novel video question answering (Video QA) task, DramaQA, for obtaining a comprehensive understanding of a video story. The DramaQA focuses on two perspectives: 1) hierarchical QAs as an evaluation metric based on the cognitive developmental stages of human intelligence, and 2) character-centered video annotations to model the local coherence of the story. Our dataset is built upon the TV drama “Another Miss Oh” and contains 16,191 QA pairs from 23,928 video clips of various lengths, with each QA pair belonging to one of four difficulty levels. We provide a total of 217,308 annotated images with rich character-centered visual annotations and coreference resolved scripts. In addition, we provide analyses of the dataset as well as a Dual Matching Multistream model which effectively learns character-centered representations of the video to answer questions about the video.

Contents

요약
Abstract
1. 서론
2. DramaQA 데이터셋
3. Dual Matching Multistream 모델
4. 실험 결과
5. 결론
References

References (9)

Add References

Recommendations

It is an article recommended by DBpia according to the article similarity. Check out the related articles!

Related Authors

Frequently Viewed Together

Recently viewed articles

Comments(0)

0

Write first comments.

UCI(KEPA) : I410-ECN-0101-2021-569-001489865