실용적인 Chart Caption 생성을 위한 계층적 접근
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 송유정 | - |
dc.contributor.author | 정성헌 | - |
dc.contributor.author | 임순범 | - |
dc.contributor.author | 이종우 | - |
dc.contributor.author | 박주현 | - |
dc.date.accessioned | 2024-04-26T08:30:22Z | - |
dc.date.available | 2024-04-26T08:30:22Z | - |
dc.date.issued | 2024-03 | - |
dc.identifier.issn | 1229-7771 | - |
dc.identifier.uri | https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/159908 | - |
dc.description.abstract | Numerous attempts to interpret charts have historically been more focused on enhancing per formance rather than aligning with human practicality, inadvertently steering us away from the fundamental objective. Given that the subjective knowledge in interpreting charts varies depending on its application, it is imperative to ensure autonomy in interpretation based on foundational information. This necessitates the provision of intuitive information grounded in human perception hierarchically. We propose a methodological expansion of caption usage, termed “Caption Hierarchical Segmentation”, which progressively augments caption information based on the spatial characteristics of tokens, offer ing multi-layered captions. This approach facilitates the training of models to be versatile in application, grounded in human perceptibility. Our method, when integrated with existing chart explanation models, serves to prevent misunderstandings and overfitting by the model. It achieves this by offering simple explanations for samples that are otherwise uninterpretable, thereby providing only intuitive information and averting incorrect responses. | - |
dc.format.extent | 10 | - |
dc.language | 한국어 | - |
dc.language.iso | KOR | - |
dc.publisher | 한국멀티미디어학회 | - |
dc.title | 실용적인 Chart Caption 생성을 위한 계층적 접근 | - |
dc.title.alternative | A Hierarchical Approach to Creating Practical Chart Captions | - |
dc.type | Article | - |
dc.publisher.location | 대한민국 | - |
dc.identifier.doi | 10.9717/kmms.2024.27.3.400 | - |
dc.identifier.bibliographicCitation | 멀티미디어학회논문지, v.27, no.3, pp 400 - 409 | - |
dc.citation.title | 멀티미디어학회논문지 | - |
dc.citation.volume | 27 | - |
dc.citation.number | 3 | - |
dc.citation.startPage | 400 | - |
dc.citation.endPage | 409 | - |
dc.identifier.kciid | ART003064022 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | kci | - |
dc.subject.keywordAuthor | Charts Interpretation | - |
dc.subject.keywordAuthor | Human Practicality | - |
dc.subject.keywordAuthor | Caption Hierarchical Segmentation | - |
dc.subject.keywordAuthor | Visually Impaired | - |
dc.subject.keywordAuthor | Chart Image Description | - |
dc.identifier.url | https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE11744552&language=ko_KR&hasTopBanner=true | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
Sookmyung Women's University. Cheongpa-ro 47-gil 100 (Cheongpa-dong 2ga), Yongsan-gu, Seoul, 04310, Korea02-710-9127
Copyright©Sookmyung Women's University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.