지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술대회자료
- 저자정보
- 발행연도
- 2024.11
- 수록면
- 870 - 874 (5page)
이용수
초록· 키워드
오류제보하기
In Knowledge-Based Visual Question Answering (KB-VQA), which requires external knowledge for accurate question answering, significant advancements have been made through the use of Large Language Models (LLMs). BLIP-2, a popular multimodal LLM, employs a single-layer Q-Former for visual feature extraction and cross-modal interactions but faces challenges with complex reasoning tasks.
To overcome these limitations, we propose integrating the Multimodal Co-Attention Network (MCAN), which uses a multi-layered approach to enhance the interaction between visual and textual inputs. Additionally, we introduce Question-Aware Prompts during fine-tuning, combining Answer Candidates with confidence scores and Answer-Aware Examples from past cases. This improves the model's ability to interpret questions accurately and generate more contextually appropriate answers.
Experimental results on KB-VQA datasets show a 6.9% improvement in accuracy compared to baseline models, demonstrating the effectiveness of our approach in handling complex multimodal reasoning tasks.
To overcome these limitations, we propose integrating the Multimodal Co-Attention Network (MCAN), which uses a multi-layered approach to enhance the interaction between visual and textual inputs. Additionally, we introduce Question-Aware Prompts during fine-tuning, combining Answer Candidates with confidence scores and Answer-Aware Examples from past cases. This improves the model's ability to interpret questions accurately and generate more contextually appropriate answers.
Experimental results on KB-VQA datasets show a 6.9% improvement in accuracy compared to baseline models, demonstrating the effectiveness of our approach in handling complex multimodal reasoning tasks.
목차
Abstract
I. 서론
II. 본론
Ⅲ. 실험
Ⅳ. 결론 및 향후 연구 방향
참고문헌
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
A Probabilistic Visual Question Answering Model Based VQA
한국컴퓨터게임학회논문지
2022 .09
-
QUESTION & ANSWER
콘크리트학회지
2018 .05
-
구조적 주의 집중 모델을 활용한 지식 기반 시각 질의 응답
한국정보과학회 학술발표논문집
2020 .07
-
Q & A / QUESTION & ANSWER
콘크리트학회지
2017 .05
-
Q&A / QUESTION & ANSWER
콘크리트학회지
2016 .07
-
Q&A / QUESTION & ANSWER
콘크리트학회지
2016 .09
-
Q & A / QUESTION & ANSWER
콘크리트학회지
2016 .11
-
Q & A / QUESTION & ANSWER
콘크리트학회지
2016 .01
-
Q & A / QUESTION & ANSWER
콘크리트학회지
2017 .07
-
Q & A / QUESTION & ANSWER
콘크리트학회지
2015 .05
-
Q&A / QUESTION & ANSWER
콘크리트학회지
2015 .07
-
Q & A / QUESTION & ANSWER
콘크리트학회지
2015 .09
-
Q & A / QUESTION & ANSWER
콘크리트학회지
2017 .11
-
Q & A / QUESTION & ANSWER
콘크리트학회지
2018 .01
-
Q & A / QUESTION & ANSWER
콘크리트학회지
2018 .03
-
Q & A | QUESTION & ANSWER
콘크리트학회지
2017 .09
-
Q & A / QUESTION & ANSWER
콘크리트학회지
2017 .03
-
Q & A / QUESTION & ANSWER
콘크리트학회지
2017 .01
-
Q&A / QUESTION & ANSWER
콘크리트학회지
2015 .11
-
이미지 태그를 활용한 시각질의응답 시스템
한국정보과학회 학술발표논문집
2018 .06
최근 본 자료
댓글(0)
0