{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T20:41:03Z","timestamp":1779914463344,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","funder":[{"name":"STEMMA PRIN project thanks to the funding by the European Union - Next Generation EU","award":["B53D23019500006"],"award-info":[{"award-number":["B53D23019500006"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,6]]},"DOI":"10.1145\/3750069.3750122","type":"proceedings-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T15:38:17Z","timestamp":1760456297000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Descriptive Review of Image Datasets for Accessible Alternative Descriptions in STEM Domains"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0458-589X","authenticated-orcid":false,"given":"Marco","family":"Cardia","sequence":"first","affiliation":[{"name":"University of Pisa, Pisa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1725-9433","authenticated-orcid":false,"given":"Marina","family":"Buzzi","sequence":"additional","affiliation":[{"name":"CNR - IIT, Pisa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6185-0795","authenticated-orcid":false,"given":"Giulio","family":"Galesi","sequence":"additional","affiliation":[{"name":"University of Pisa, Pisa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2469-9648","authenticated-orcid":false,"given":"Barbara","family":"Leporini","sequence":"additional","affiliation":[{"name":"University of Pisa, Pisa, Italy and CNR - ISTI, Pisa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Karla Antonelli Anne Steverson and Jamie O\u2019Mally. 2018. College graduates with visual impairments: A report on seeking and finding employment. Journal of Visual Impairment & Blindness 112 1 (2018) 33\u201345.","DOI":"10.1177\/0145482X1811200104"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"R. Bernardi R. Cakici D. Elliott A. Erdem E. Erdem N. Ikizler-Cinbis F. Keller A. Muscat and B. Plank. 2016. Automatic description generation from images: A survey of models datasets and evaluation measures. Journal of Artificial Intelligence Research 55 (2016) 409\u2013442.","DOI":"10.1613\/jair.4900"},{"key":"e_1_3_3_1_4_2","volume-title":"International workshop ontoImage","author":"Grubinger Michael","year":"2006","unstructured":"Michael Grubinger, Paul Clough, Henning M\u00fcller, and Thomas Deselaers. 2006. The iapr tc-12 benchmark: A new evaluation resource for visual information systems. In International workshop ontoImage , Vol.\u00a02."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Jesse\u00a0R Hairston Derrick\u00a0W Smith Tania Williams William\u00a0T Sabados and Steven Forney. 2020. Teaching cybersecurity to students with visual impairments and blindness. Journal of Science Education for Students with Disabilities 23 1 (2020) n1.","DOI":"10.14448\/jsesd.12.0007"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Cicely Hayes and Michael\u00a0J Proulx. 2024. Turning a blind eye? Removing barriers to science and mathematics education for students with visual impairments. British Journal of Visual Impairment 42 2 (2024) 544\u2013556.","DOI":"10.1177\/02646196221149561"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Micah Hodosh Peter Young and Julia Hockenmaier. 2013. Framing image description as a ranking task: Data models and evaluation metrics. Journal of Artificial Intelligence Research 47 (2013) 853\u2013899.","DOI":"10.1613\/jair.3994"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"T.Y. Hsu C.L. Giles and T.H. Huang. 2021. Scicap: Generating captions for scientific figures. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.11624 (2021).","DOI":"10.18653\/v1\/2021.findings-emnlp.277"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681294"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICITEICS61368.2024.10624906"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"e_1_3_3_1_13_2","unstructured":"Samira\u00a0Ebrahimi Kahou Vincent Michalski Adam Atkinson \u00c1kos K\u00e1d\u00e1r Adam Trischler and Yoshua Bengio. 2017. Figureqa: An annotated figure dataset for visual reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1710.07300 (2017)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.277"},{"key":"e_1_3_3_1_15_2","unstructured":"Z. Karishma S. Rohatgi K.S. Puranik J. Wu and C.L. Giles. 2023. Acl-fig: A dataset for scientific figure classification. https:\/\/arxiv.org\/abs\/2301.12293."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"e_1_3_3_1_17_2","unstructured":"Jaeyoung Kim Jongho Lee Hong-Jun Choi Ting-Yao Hsu Chieh-Yang Huang Sungchul Kim Ryan Rossi Tong Yu Clyde\u00a0Lee Giles Ting-Hao\u2019Kenneth\u2019 Huang et\u00a0al. 2025. Multi-LLM Collaborative Caption Generation in Scientific Documents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.02552 (2025)."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"M. Leotta F. Mori and M. Ribaudo. 2023. Evaluating the effectiveness of automatic image captioning for web accessibility. Universal Access in the Information Society 22 4 (2023) 1293\u20131313.","DOI":"10.1007\/s10209-022-00906-7"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.775"},{"key":"e_1_3_3_1_20_2","unstructured":"Z. Li X. Yang K. Choi W. Zhu R. Hsieh H. Kim J.H. Lim S. Ji B. Lee X. Yan et\u00a0al. 2024. MMSCI: A dataset for graduate-level multi-discipline multimodal scientific understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.04903 (2024)."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Alex Lundgard and Arvind Satyanarayan. 2021. Accessible visualization via natural language descriptions: A four-level model of semantic content. IEEE Transactions on Visualization and Computer Graphics 28 1 (2021) 1073\u20131083.","DOI":"10.1109\/TVCG.2021.3114770"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471207"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Ahmed Masry Dongxu Long Jiaqi Tan Shafiq Joty and Enamul Hoque. 2022. ChartQA: A benchmark for question answering about charts with visual and logical reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.10244 (2022).","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Jason Obeid and Enamul Hoque. 2020. Chart-to-text: Generating natural language descriptions for charts by adapting the transformer model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.09142 (2020).","DOI":"10.18653\/v1\/2020.inlg-1.20"},{"key":"e_1_3_3_1_27_2","unstructured":"Vicente Ordonez Girish Kulkarni and Tamara Berg. 2011. Im2text: Describing images using 1 million captioned photographs. Advances in neural information processing systems 24 (2011)."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1515\/kbo-2018-0115"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.21428\/594757db.0b1f96f6"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Himanshu Sharma and Devanand Padha. 2023. A comprehensive survey on image captioning: from handcrafted to deep learning-based techniques a taxonomy and open research issues. Artificial Intelligence Review 56 11 (2023) 13619\u201313661.","DOI":"10.1007\/s10462-023-10488-2"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Bruno Splendiani. 2015. A proposal for the inclusion of accessibility criteria in the authoring workflow of images for scientific articles.","DOI":"10.1016\/j.procs.2015.09.250"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3493612.3520449"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Z. Yang R. Dabre H. Tanaka and N. Okazaki. 2024. Scicap+: A knowledge augmented dataset to study the challenges of scientific figure captioning. Journal of Natural Language Processing 31 3 (2024) 1140\u20131165.","DOI":"10.5715\/jnlp.31.1140"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Yelp Inc.2014. Yelp Dataset Challenge. http:\/\/www.yelp.com\/dataset_challenge. Accessed: 21 April 2025.","DOI":"10.5040\/9798216023166.ch-003"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Peter Young Alice Lai Micah Hodosh and Julia Hockenmaier. 2014. From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the association for computational linguistics 2 (2014) 67\u201378.","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_3_1_36_2","unstructured":"J. Zhu J. Ran R.K.W. Lee K. Choo and Z. Li. 2021. AutoChart: A dataset for chart-to-text generation task. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.06897 (2021)."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.387"}],"event":{"name":"CHItaly 2025: CHItaly 2025: 16th Biannual Conference of the Italian SIGCHI Chapter","location":"Salerno Italy","acronym":"CHItaly 2025"},"container-title":["Proceedings of the 16th Biannual Conference of the Italian SIGCHI Chapter"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3750069.3750122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T11:28:08Z","timestamp":1760614088000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3750069.3750122"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,6]]},"references-count":36,"alternative-id":["10.1145\/3750069.3750122","10.1145\/3750069"],"URL":"https:\/\/doi.org\/10.1145\/3750069.3750122","relation":{},"subject":[],"published":{"date-parts":[[2025,10,6]]},"assertion":[{"value":"2025-10-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}