{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T00:59:43Z","timestamp":1792803583039,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T00:00:00Z","timestamp":1681862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,19]]},"DOI":"10.1145\/3544548.3580921","type":"proceedings-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T04:27:20Z","timestamp":1681964840000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Slide Gestalt: Automatic Structure Extraction in Slide Decks for Non-Visual Access"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6335-5904","authenticated-orcid":false,"given":"Yi-Hao","family":"Peng","sequence":"first","affiliation":[{"name":"Human-Computer Interaction Institute, Carnegie Mellon University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8511-2834","authenticated-orcid":false,"given":"Peggy","family":"Chi","sequence":"additional","affiliation":[{"name":"Google Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9982-5536","authenticated-orcid":false,"given":"Anjuli","family":"Kannan","sequence":"additional","affiliation":[{"name":"Google, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1436-9223","authenticated-orcid":false,"given":"Meredith Ringel","family":"Morris","sequence":"additional","affiliation":[{"name":"Google Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6236-2969","authenticated-orcid":false,"given":"Irfan","family":"Essa","sequence":"additional","affiliation":[{"name":"Google Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,4,19]]},"reference":[{"key":"e_1_3_3_3_1_1","unstructured":"Shadi Abou-Zahra and EOWG Participants. 2020. How to Make Your Presentations Accessible to All. https:\/\/www.w3.org\/WAI\/teach-advocate\/accessible-presentations\/#preparing-slides-and-projected-material-speakers."},{"key":"e_1_3_3_3_2_1","volume-title":"Apple. Retrieved","year":"2022","unstructured":"Apple. 2022. Group or ungroup slides in Keynote on Mac - Apple Support. Apple. Retrieved September, 2022 from https:\/\/support.apple.com\/guide\/keynote\/group-or-ungroup-slides-tan98841ef85\/mac"},{"key":"e_1_3_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1719970.1719999"},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2851581.2892588"},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1168987.1169018"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14100-3_51"},{"key":"e_1_3_3_3_7_1","unstructured":"Chilli Breeze. 2022. Common Design of PowerPoint. https:\/\/www.chillibreeze.com\/presentation-design\/6-must-have-layout-slides-for-your-business-powerpoint-templates\/."},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2380116.2380130"},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557254"},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1166253.1166263"},{"key":"e_1_3_3_3_11_1","unstructured":"Nancy Duarte. 2008. Slide: ology: The art and science of creating great presentations. Vol.\u00a01. O\u2019Reilly Media Sebastapol."},{"key":"e_1_3_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2470749"},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2898970"},{"key":"e_1_3_3_3_14_1","unstructured":"Mirette et\u00a0al. Elias. 2018. SlideWiki: towards a collaborative and accessible platform for slide presentations."},{"key":"e_1_3_3_3_15_1","unstructured":"Vocal Eyes. 2018. Making your conference presentation more accessible to blind and partially sighted people. https:\/\/vocaleyes.co.uk\/services\/resources\/guidelines-for-making-your-conference-presentation-more-accessible-to-blind-and-partially-sighted-people\/."},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502143"},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376437"},{"key":"e_1_3_3_3_18_1","volume-title":"Topic Transition in Educational Videos Using Visually Salient Words","author":"Gandhi Ankit","year":"2015","unstructured":"Ankit Gandhi, Arijit Biswas, and Om Deshmukh. 2015. Topic Transition in Educational Videos Using Visually Salient Words.International Educational Data Mining Society (2015)."},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376728"},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave"},{"key":"e_1_3_3_3_21_1","volume-title":"Google. Retrieved","year":"2022","unstructured":"Google. 2022. Google Slides API | Google Developers. Google. Retrieved September, 2022 from https:\/\/developers.google.com\/slides\/api"},{"key":"e_1_3_3_3_22_1","volume-title":"Google. Retrieved","year":"2022","unstructured":"Google. 2022. Google Slides: Online Slideshow Maker | Google Workspace. Google. Retrieved September, 2022 from https:\/\/www.google.com\/slides\/about\/"},{"key":"e_1_3_3_3_23_1","volume-title":"Google. Retrieved","year":"2022","unstructured":"Google. 2022. Vision AI | Derive Image Insights via ML | Cloud Vision API | Google Cloud. Google. Retrieved September, 2022 from https:\/\/cloud.google.com\/vision"},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89197-0_62"},{"key":"e_1_3_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/332040.332427"},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581494"},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1168987.1169016"},{"key":"e_1_3_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/226159.226161"},{"key":"e_1_3_3_3_29_1","volume-title":"Graph-rise: Graph-regularized image semantic embedding. arXiv preprint arXiv:1902.10814(2019).","author":"Juan Da-Cheng","year":"2019","unstructured":"Da-Cheng Juan, Chun-Ta Lu, Zhen Li, Futang Peng, Aleksei Timofeev, Yi-Ting Chen, Yaxi Gao, Tom Duerig, Andrew Tomkins, and Sujith Ravi. 2019. Graph-rise: Graph-regularized image semantic embedding. arXiv preprint arXiv:1902.10814(2019)."},{"key":"e_1_3_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2015.11.012"},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1414471.1414500"},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2019.8798065"},{"key":"e_1_3_3_3_33_1","volume-title":"Making your presentation accessible. interactions 24, 4","author":"Ladner E","year":"2017","unstructured":"Richard\u00a0E Ladner and Kyle Rector. 2017. Making your presentation accessible. interactions 24, 4 (2017), 56\u201359."},{"key":"e_1_3_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501966"},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3476548"},{"key":"e_1_3_3_3_36_1","volume-title":"Dit: Self-supervised pre-training for document image transformer. arXiv preprint arXiv:2203.02378(2022).","author":"Li Junlong","year":"2022","unstructured":"Junlong Li, Yiheng Xu, Tengchao Lv, Lei Cui, Cha Zhang, and Furu Wei. 2022. Dit: Self-supervised pre-training for document image transformer. arXiv preprint arXiv:2203.02378(2022)."},{"key":"e_1_3_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/958432.958476"},{"key":"e_1_3_3_3_38_1","volume-title":"Microsoft. Retrieved","year":"2022","unstructured":"Microsoft. 2022. Organize slides into sections. Microsoft. Retrieved September, 2022 from https:\/\/support.microsoft.com\/en-us\/office\/organize-your-powerpoint-slides-into-sections-de4bf162-e9cc-4f58-b64a-7ab09443b9f8"},{"key":"e_1_3_3_3_39_1","unstructured":"Microsoft. 2022. PowerPoint Accessibility. https:\/\/support.microsoft.com\/en-us\/office\/make-your-powerpoint-presentations-accessible-to-people-with-disabilities-6f7772b2-2f33-4bd2-8ca7-dae3b2b3ef25."},{"key":"e_1_3_3_3_40_1","doi-asserted-by":"crossref","unstructured":"Sheshera Mysore Arman Cohan and Tom Hope. 2021. Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity. arXiv preprint arXiv:2111.08366(2021).","DOI":"10.18653\/v1\/2022.naacl-main.331"},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471201"},{"key":"e_1_3_3_3_42_1","unstructured":"Bureau of Internet\u00a0Accessibility. 2018. Tips for Making Your Presentations Accessible. https:\/\/www.boia.org\/blog\/tips-for-making-your-presentations-accessible."},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807442.2807502"},{"key":"e_1_3_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415864"},{"key":"e_1_3_3_3_45_1","volume-title":"Slidecho: Flexible Non-Visual Exploration of Presentation Videos. In The 23rd International ACM SIGACCESS Conference on Computers and Accessibility. 1\u201312","author":"Peng Yi-Hao","year":"2021","unstructured":"Yi-Hao Peng, Jeffrey\u00a0P Bigham, and Amy Pavel. 2021. Slidecho: Flexible Non-Visual Exploration of Presentation Videos. In The 23rd International ACM SIGACCESS Conference on Computers and Accessibility. 1\u201312."},{"key":"e_1_3_3_3_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173867"},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445572"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300913"},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545637"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2020.00033"},{"key":"e_1_3_3_3_51_1","volume-title":"Presentation Zen: Simple ideas on presentation design and delivery.","author":"Reynolds Garr","year":"2011","unstructured":"Garr Reynolds. 2011. Presentation Zen: Simple ideas on presentation design and delivery. New Riders, Indianapolis, IN, USA."},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"crossref","unstructured":"Masoud\u00a0Jalili Sabet Philipp Dufter Fran\u00e7ois Yvon and Hinrich Sch\u00fctze. 2020. SimAlign: High quality word alignments without parallel training data using static and contextualized embeddings. arXiv preprint arXiv:2004.08728(2020).","DOI":"10.18653\/v1\/2020.findings-emnlp.147"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03655-2_41"},{"key":"e_1_3_3_3_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/1168987.1169041"},{"key":"e_1_3_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445242"},{"key":"e_1_3_3_3_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469096.3474939"},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2166966.2166992"},{"key":"e_1_3_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2379790.2379795"},{"key":"e_1_3_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445721"},{"key":"e_1_3_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397868"},{"key":"e_1_3_3_3_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581158"},{"key":"e_1_3_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818709"},{"key":"e_1_3_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517615"},{"key":"e_1_3_3_3_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/2596695.2596720"},{"key":"e_1_3_3_3_65_1","volume-title":"Proceedings of the 2003 ACM SIGGRAPH\/Eurographics Symposium on Computer Animation","author":"E.","unstructured":"Douglas\u00a0E. Zongker and David\u00a0H. Salesin. 2003. On Creating Animated Presentations. In Proceedings of the 2003 ACM SIGGRAPH\/Eurographics Symposium on Computer Animation (San Diego, California) (SCA \u201903). Eurographics Association, Goslar, DEU, 298\u2013308."}],"event":{"name":"CHI '23: CHI Conference on Human Factors in Computing Systems","location":"Hamburg Germany","acronym":"CHI '23","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3544548.3580921","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3544548.3580921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:19Z","timestamp":1750178839000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3544548.3580921"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,19]]},"references-count":65,"alternative-id":["10.1145\/3544548.3580921","10.1145\/3544548"],"URL":"https:\/\/doi.org\/10.1145\/3544548.3580921","relation":{},"subject":[],"published":{"date-parts":[[2023,4,19]]},"assertion":[{"value":"2023-04-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}