메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술저널
저자정보
Yeong-Jae Shin (Korea Maritime & Ocean University) Seong-Beom Jeong (Korea Maritime & Ocean University) Ju-Hyeon Seong (Korea Maritime & Ocean University) Dong-Hoan Seo (Korea Maritime & Ocean University)
저널정보
한국마린엔지니어링학회 Journal of Advanced Marine Engineering and Technology (JAMET) 한국마린엔지니어링학회지 제46권 제6호
발행연도
2022.12
수록면
422 - 429 (8page)
DOI
10.5916/jamet.2022.46.6.422

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
Context recognition is a technology that acquires information about events based on information on various objects appearing in images. To implement this, dense image captioning, which recognizes all objects in an image, is often applied. However, because this approach targets all objects, it provides status information, such as location or color, which is relatively less important to humans, and even static object information. To humans, this information is unnecessary because of its low readability. To solve this problem, we propose a Context Pair Network that describes only the context of an object based on visual relationship detection. The proposed model consists of a pair object module (POM) that extracts subjects, objects, and relationships and a pair embedding module (PEM) that creates a subject–predicate–object structure. The proposed POM detects objects corresponding to subjects and objects based on three RCNNs and matches the detected objects with subject–object (S-O) pairs. The PEM also generates sentences consisting of a subject–predicate–object using S-O pairs based on long short-term memory. Thus, the proposed model is capable of situational awareness that provides only interactions between objects, unlike conventional captioning, which describes all the information indiscriminately.

목차

Abstract
1. Introduction
2. Related studies
3. Proposed dense image captioning
4. Experiment and result
5. Conclusion
References

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2023-559-000332985