{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T16:03:53Z","timestamp":1776096233299,"version":"3.50.1"},"reference-count":61,"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":"European Commission through the Ability: Haptic Tablet for the Accessibility of Digital Content to the Visually Impaired (ABILITY) Project","award":["101070396"],"award-info":[{"award-number":["101070396"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3605490","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:31:52Z","timestamp":1756834312000},"page":"156072-156090","source":"Crossref","is-referenced-by-count":1,"title":["Semi-Automatic BVI Human-Centered Image Conversational Descriptions: Leveraging LLMs and Expert Refinements for Inclusive Visual Accessibility"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7546-4657","authenticated-orcid":false,"given":"Mazen","family":"Salous","sequence":"first","affiliation":[{"name":"OFFIS Institute for Information Technology, Oldenburg, Germany"}]},{"given":"Daniel","family":"Lange","sequence":"additional","affiliation":[{"name":"OFFIS Institute for Information Technology, Oldenburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0674-1843","authenticated-orcid":false,"given":"Timo","family":"von Reeken","sequence":"additional","affiliation":[{"name":"OFFIS Institute for Information Technology, Oldenburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3369-3558","authenticated-orcid":false,"given":"Maria K.","family":"Wolters","sequence":"additional","affiliation":[{"name":"OFFIS Institute for Information Technology, Oldenburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2085-193X","authenticated-orcid":false,"given":"Wilko","family":"Heuten","sequence":"additional","affiliation":[{"name":"OFFIS Institute for Information Technology, Oldenburg, Germany"}]},{"given":"Susanne","family":"Boll","sequence":"additional","affiliation":[{"name":"OFFIS Institute for Information Technology, Oldenburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6048-042X","authenticated-orcid":false,"given":"Larbi","family":"Abdenebaoui","sequence":"additional","affiliation":[{"name":"OFFIS Institute for Information Technology, Oldenburg, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00540"},{"key":"ref8","first-page":"9","article-title":"Audio description and social acceptability","volume":"19","author":"Matamala","year":"2017","journal-title":"Rivista Internazionale di Tecnica della Traduzione"},{"key":"ref9","article-title":"A comparative study of audio description guidelines prevalent in different countries","author":"Rai","year":"2010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2000119.2000166"},{"key":"ref11","first-page":"56","article-title":"AD4Games: Applying audio description in video games","volume-title":"Proc. 9th Adv. Res. Seminar Audio Description (ARSAD)","author":"Zhang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3715336.3735685"},{"key":"ref13","first-page":"16","article-title":"Bridging the accessibility gap? The role of AI in the future of audio description generation","volume-title":"Proc. Adv. Res. Seminar Audio Description (ARSAD)","author":"Braun"},{"key":"ref14","first-page":"11135","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Herdade"},{"key":"ref15","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2304.08485"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.68298"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2441776.2441915"},{"key":"ref20","article-title":"Towards AI-based accessible digital media: Image analysis pipelines and blind user studies","volume-title":"Proc. IEEE Int. Conf. Systems, Man, Cybernetics (SMC)","author":"Salous"},{"key":"ref21","volume-title":"Web Content Accessibility Guidelines (WCAG) 2.1","year":"2018"},{"key":"ref22","volume-title":"Maximum Accessibility: Making Your Web Site More Usable for Everyone","author":"Slatin","year":"2003"},{"issue":"2","key":"ref23","article-title":"Describing images on the web: A survey of current practice and prospects for the future","volume":"71","author":"Petrie","year":"2005","journal-title":"Proc. Hum. Comput. Interact. Int. (HCII)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2764916"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858116"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3587469"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471207"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1080\/10572252.2024.2372771"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ics.2005.05.215"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1080\/0907676X.2010.485686"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/0907676X.2012.693108"},{"key":"ref32","first-page":"71","article-title":"The heartbeat of creativity in audio description: A pilot heart rate study on multimodal objectivity and subjectivity","volume-title":"Proc. 10th Adv. Res. Seminar Audio Description (ARSAD)","author":"Romero-Mu\u00f1oz"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376404"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3638067.3638105"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-022-00906-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415864"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481291"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702329"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2809904.2809910"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.61"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2002.1024745"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1168987.1169018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v5i1.13301"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3134756"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.01.135"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-018-9650-2"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/INCET49848.2020.9154121"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465960"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3585628"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580688"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5040\/9781350906075"},{"key":"ref56","volume-title":"Insidevision: BVI-Dedicated Tablet","year":"2023"},{"issue":"2","key":"ref57","first-page":"169","article-title":"Less is more. Effects of the amount of information and its presentation in the recall and reception of audio described characters","volume":"14","author":"Fresno","year":"2014","journal-title":"Int. J. Sci., Basic Appl. Res."},{"key":"ref58","article-title":"Instruction tuning with GPT-4","author":"Peng","year":"2023","journal-title":"arXiv:2304.03277"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1177\/0264619616661603"},{"key":"ref60","first-page":"9","article-title":"Audio introductions: Telling the story to blind viewers","volume-title":"Audio Description: New Perspectives Illustrated","author":"Fryer","year":"2014"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1080\/09647775.2021.1878469"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11146787.pdf?arnumber=11146787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T04:49:17Z","timestamp":1757652557000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11146787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3605490","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}