{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T06:03:46Z","timestamp":1782281026898,"version":"3.54.5"},"reference-count":95,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Innosuisse-Swiss Innovation Agency","award":["108.047 IP-ICT"],"award-info":[{"award-number":["108.047 IP-ICT"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3571626","type":"journal-article","created":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T17:58:16Z","timestamp":1747677496000},"page":"94040-94056","source":"Crossref","is-referenced-by-count":5,"title":["Chart Accessibility: A Review of Current Alt Text Generation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6645-6110","authenticated-orcid":false,"given":"Chuqiao","family":"Yan","sequence":"first","affiliation":[{"name":"Institute of Computer Science, Zurich University of Applied Sciences (ZHAW), Winterthur, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1709-546X","authenticated-orcid":false,"given":"Hans-Peter","family":"Hutter","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Zurich University of Applied Sciences (ZHAW), Winterthur, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5411-5116","authenticated-orcid":false,"given":"Felix M.","family":"Schmitt-Koopmann","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Zurich University of Applied Sciences (ZHAW), Winterthur, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7402-5206","authenticated-orcid":false,"given":"Alireza","family":"Darvishy","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, Zurich University of Applied Sciences (ZHAW), Winterthur, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.8ae4d525"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2021.3114846"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-60884-1_29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445207"},{"key":"ref6","volume-title":"Jaws Screen Reader","year":"2024"},{"key":"ref7","volume-title":"Nvda (nonvisual Desktop Access)","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3643834.3660747"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-62846-7_35"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3493612.3520449"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675634"},{"key":"ref12","volume-title":"Create and Verify Pdf Accessibility","year":"2024"},{"key":"ref13","volume-title":"Pdf Accessibility Checker (PAC)","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313605"},{"key":"ref15","volume-title":"Images Tutorial: Complex Images","year":"2024"},{"key":"ref16","volume-title":"Describing Figures for Accessibility","year":"2024"},{"key":"ref17","volume-title":"Creating Accessible Figures and Tables","year":"2023"},{"key":"ref18","volume-title":"How To Write Alt Text and Why","year":"2024"},{"key":"ref19","volume-title":"Specific Image Description Guidelines: E-books","year":"2024"},{"key":"ref20","author":"Bureau","year":"2024","journal-title":"Data Visualization Guidelines"},{"key":"ref21","volume-title":"Accessibility At Penn State","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.inlg-1.20"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.401"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3517428.3544796"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445443"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650738"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2024.3513320"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-022-00424-5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.2992028"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3069205"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3298050"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n71"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3356566"},{"key":"ref34","article-title":"Examining user-friendly and open-sourced large GPT models: A survey on language, multimodal, and scientific GPT models","author":"Gao","year":"2023","journal-title":"arXiv:2308.14149"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2021.3114770"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/vis54862.2022.00017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14519"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14298"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471202"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5753\/jbcs.2023.2301"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584099"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-62846-7_38"},{"key":"ref43","article-title":"An introduction to vision-language modeling","author":"Bordes","year":"2024","journal-title":"arXiv:2405.17247"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3369699"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.277"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21428\/594757db.0b1f96f6"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.277"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.inlg-main.6"},{"key":"ref50","article-title":"FigCaps-HF: A figure-to-caption generative framework and benchmark with human feedback","author":"Singh","year":"2023","journal-title":"arXiv:2307.10867"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-072-4_183"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/vis54862.2022.00016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"ref54","article-title":"ChartLlama: A multimodal LLM for chart understanding and generation","author":"Han","year":"2023","journal-title":"arXiv:2311.16483"},{"key":"ref55","first-page":"3057","article-title":"Chartthinker: A contextual chain-of-thought approach to optimized chart summarization","volume-title":"Proc. Joint Int. Conf. Comput. Linguistics, Lang. Resour. Eval.","author":"Liu"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.463"},{"key":"ref57","article-title":"TinyChart: Efficient chart understanding with visual token merging and program-of-thoughts learning","author":"Zhang","year":"2024","journal-title":"arXiv:2404.16635"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3399715.3399829"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/pacificvis48177.2020.1043"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.85"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"issue":"140","key":"ref62","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.cola.2022.101107"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/iwssip.2019.8787299"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6168-2"},{"key":"ref66","first-page":"1931","article-title":"Unifying vision-andlanguage tasks via text generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cho"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00636"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s12650-022-00894-z"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-010-0305-0"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"ref71","first-page":"18893","article-title":"Pix2Struct: Screenshot parsing as pretraining for visual language understanding","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref72","article-title":"OCR-free document understanding transformer","author":"Kim","year":"2021","journal-title":"arXiv:2111.15664"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref75","article-title":"SPHINX: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023","journal-title":"arXiv:2311.07575"},{"key":"ref76","author":"Face","year":"2023","journal-title":"Introducing Idefics: Image Understanding At Scale"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01100"},{"key":"ref78","article-title":"Textbooks are all you need II: Phi-1.5 technical report","volume-title":"arXiv:2309.05463","author":"Li","year":"2023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-6319"},{"key":"ref81","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches out","author":"Lin"},{"key":"ref82","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref83","first-page":"223","article-title":"A study of translation error rate with targeted human annotation","volume-title":"Proc. 7th Conf. Assoc. Mach. Transl. Americas (AMTA)","author":"Snover"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"ref85","first-page":"957","article-title":"From word embeddings to document distances","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kusner"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1239"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7299087"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.3115\/1220575.1220617"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3640543.3645212"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517431"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581186"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642730"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15099"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3640543.3645175"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11007153.pdf?arnumber=11007153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T17:57:54Z","timestamp":1749059874000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11007153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":95,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3571626","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}