{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T01:03:18Z","timestamp":1792803798943,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":140,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,28]]},"DOI":"10.1145\/3746059.3747756","type":"proceedings-article","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T07:44:49Z","timestamp":1758959089000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["StreetViewAI: Making Street View Accessible Using Context-Aware Multimodal AI"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8291-3353","authenticated-orcid":false,"given":"Jon E.","family":"Froehlich","sequence":"first","affiliation":[{"name":"Google Research, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8981-1114","authenticated-orcid":false,"given":"Alexander J.","family":"Fiannaca","sequence":"additional","affiliation":[{"name":"Google DeepMind, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7326-1156","authenticated-orcid":false,"given":"Nimer M","family":"Jaber","sequence":"additional","affiliation":[{"name":"Google, Mountainview, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4860-9138","authenticated-orcid":false,"given":"Victor","family":"Tsaran","sequence":"additional","affiliation":[{"name":"Google, Mountain View, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0276-9417","authenticated-orcid":false,"given":"Shaun K.","family":"Kane","sequence":"additional","affiliation":[{"name":"Google Research, Boulder, Colorado, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM.2019.8767407"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2935334.2935361"},{"key":"e_1_3_3_3_4_2","unstructured":"Aira. 2025. Aira: Video Remote Interpreting. https:\/\/aira.io\/ Remote video interpreting service for blind low-vision deaf and hard-of-hearing communities."},{"key":"e_1_3_3_3_5_2","unstructured":"Temitope Akinboyewa Zhenlong Li Huan Ning and M.\u00a0Naser Lessani. 2024. GIS Copilot: Towards an Autonomous GIS Agent for Spatial Analysis. arxiv:https:\/\/arXiv.org\/abs\/2411.03205\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2411.03205"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292147.3292163"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_3_3_8_2","unstructured":"Apple Inc.2024. Get live descriptions of your surroundings on iPhone. Apple Support. https:\/\/support.apple.com\/guide\/iphone\/get-live-descriptions-of-your-surroundings-iph37e6b3844\/ios Accessed: April 9 2025."},{"key":"e_1_3_3_3_9_2","unstructured":"Apple Inc.2024. Use VoiceOver Recognition on your iPhone or iPad. Apple Support. https:\/\/support.apple.com\/en-us\/111799 Accessed: April 9 2025."},{"key":"e_1_3_3_3_10_2","unstructured":"Apple Inc.2025. Apple Look Around. https:\/\/www.apple.com\/maps\/"},{"key":"e_1_3_3_3_11_2","unstructured":"Matthew\u00a0Tylee Atkinson. 2018. AGRIP: Accessible Gaming Rendering Independence Possible \/ AudioQuake. https:\/\/github.com\/matatk\/agrip"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/1183316.1183321"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","unstructured":"Vahid Balali Armin Ashouri\u00a0Rad and Mani Golparvar-Fard. 2015. Detection classification and mapping of U.S. traffic signs using google street view images for roadway inventory management. Visualization in Engineering 3 1 (11 2015) 15. 10.1186\/s40327-015-0027-1","DOI":"10.1186\/s40327-015-0027-1"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471224"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","unstructured":"Alejandro Barredo Arrieta Natalia D\u00edaz-Rodr\u00edguez Javier Del Ser Adrien Bennetot Siham Tabik Alberto Barbado Salvador Garcia Sergio Gil-Lopez Daniel Molina Richard Benjamins Raja Chatila and Francisco Herrera. 2020. Explainable Artificial Intelligence (XAI): Concepts taxonomies opportunities and challenges toward responsible AI. Information Fusion 58 (2020) 82\u2013115. 10.1016\/j.inffus.2019.12.012","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"e_1_3_3_3_16_2","unstructured":"Be My Eyes. 2025. Be My AI. https:\/\/www.bemyeyes.com\/blog\/be-my-ai-launches-globally"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3170427.3185373"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676375"},{"key":"e_1_3_3_3_19_2","unstructured":"Junlong Chen Rosella P.\u00a0Galindo Esparza Vanja Garaj Per\u00a0Ola Kristensson and John Dudley. 2025. EnVisionVR: A Scene Interpretation Tool for Visual Accessibility in Virtual Reality. arxiv:https:\/\/arXiv.org\/abs\/2502.03564\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2502.03564"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","unstructured":"Liang-Chieh Chen George Papandreou Iasonas Kokkinos Kevin Murphy and Alan\u00a0L. Yuille. 2018. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets Atrous Convolution and Fully Connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence 40 4 (2018) 834\u2013848. 10.1109\/TPAMI.2017.2699184","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708359.3712082"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675613"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","unstructured":"Victoria Clarke and Virginia\u00a0Braun and. 2017. Thematic analysis. The Journal of Positive Psychology 12 3 (2017) 297\u2013298. 10.1080\/17439760.2016.1262613 arXiv:10.1080\/17439760.2016.1262613","DOI":"10.1080\/17439760.2016.1262613"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3688498"},{"key":"e_1_3_3_3_25_2","unstructured":"Megan Conway Brett Oppegaard and Tuyet Hayes. 2020. Audio description: Making useful maps for blind and visually impaired people. Technical Communication 67 2 (2020) 68\u201386."},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3688537"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","unstructured":"Yuri Danilov and Mitchell Tyler. 2005. Brainport: An Alternative Input to the Brain. Journal of Integrative Neuroscience 04 04 (2005) 537\u2013550. 10.1142\/S0219635205000914 arXiv:10.1142\/S0219635205000914","DOI":"10.1142\/S0219635205000914"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","unstructured":"Franco Delogu Massimiliano Palmiero Stefano Federici Catherine Plaisant Haixia Zhao and Olivetti\u00a0Belardinelli and. 2010. Non-visual exploration of geographic maps: Does sonification help? Disability and Rehabilitation: Assistive Technology 5 3 (2010) 164\u2013174. 10.3109\/17483100903100277 arXiv:10.3109\/17483100903100277 PMID: 20415530.","DOI":"10.3109\/17483100903100277"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","unstructured":"Pierre Dognin Igor Melnyk Youssef Mroueh Inkit Padhi Mattia Rigotti Jarret Ross Yair Schiff Richard\u00a0A. Young and Brian Belgodere. 2022. Image Captioning as an Assistive Technology: Lessons Learned from VizWiz 2020 Challenge. Journal of Artificial Intelligence Research 73 (Jan. 2022) 437\u2013459. 10.1613\/jair.1.13113","DOI":"10.1613\/jair.1.13113"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3517428.3550381"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54446-517"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","unstructured":"John Dudley Lulu Yin Vanja Garaj and Per\u00a0Ola Kristensson. 2023. Inclusive Immersion: a review of efforts to improve accessibility in virtual reality augmented reality and the metaverse. Virtual Reality 27 4 (12 2023) 2989\u20133020. 10.1007\/s10055-023-00850-8","DOI":"10.1007\/s10055-023-00850-8"},{"key":"e_1_3_3_3_34_2","unstructured":"Freedom Scientific. 2025. JAWS Screen Reader. https:\/\/www.freedomscientific.com\/products\/software\/jaws\/"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","unstructured":"Jon\u00a0E. Froehlich Anke\u00a0M. Brock Anat Caspi Jo\u00e3o Guerreiro Kotaro Hara Reuben Kirkham Johannes Sch\u00f6ning and Benjamin Tannert. 2019. Grand challenges in accessible maps. 26 2 (Feb. 2019) 78\u201381. 10.1145\/3301657","DOI":"10.1145\/3301657"},{"key":"e_1_3_3_3_36_2","unstructured":"GMA Games. 2025. Shades of Doom. https:\/\/www.gmagames.com\/sod.html"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1002\/9780470379424.ch25"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313605"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","unstructured":"Cole Gleason Alexander\u00a0J. Fiannaca Melanie Kneisel Edward Cutrell and Meredith\u00a0Ringel Morris. 2018. FootNotes: Geo-referenced Audio Annotations for Nonvisual Exploration. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 2 3 Article 109 (Sept. 2018) 24\u00a0pages. 10.1145\/3264919","DOI":"10.1145\/3264919"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642211"},{"key":"e_1_3_3_3_41_2","unstructured":"GoodMaps Inc.2025. GoodMaps. https:\/\/goodmaps.com\/"},{"key":"e_1_3_3_3_42_2","unstructured":"Google. 2023. Voice Guidance in Maps Built for People with Impaired Vision. https:\/\/blog.google\/products\/maps\/better-maps-for-people-with-vision-impairments\/ Official Google blog post about accessibility features in Google Maps."},{"key":"e_1_3_3_3_43_2","unstructured":"Google. 2024. Use image descriptions in TalkBack. Android Accessibility Help. https:\/\/support.google.com\/accessibility\/android\/answer\/15341968 Accessed: April 9 2025."},{"key":"e_1_3_3_3_44_2","unstructured":"Google. 2025. Celebrate 15 years of exploring your world on Street View. https:\/\/www.google.com\/streetview\/anniversary\/"},{"key":"e_1_3_3_3_45_2","unstructured":"Google. 2025. Google Cloud Speech-to-Text API. https:\/\/cloud.google.com\/speech-to-text"},{"key":"e_1_3_3_3_46_2","unstructured":"Google. 2025. Google Cloud Text-to-Speech API. https:\/\/cloud.google.com\/text-to-speech"},{"key":"e_1_3_3_3_47_2","unstructured":"Google. 2025. Google Gemini API. https:\/\/ai.google.dev\/gemini-api\/docs\/models"},{"key":"e_1_3_3_3_48_2","unstructured":"Google. 2025. Google Maps Places API. https:\/\/developers.google.com\/maps\/documentation\/places"},{"key":"e_1_3_3_3_49_2","unstructured":"Google. 2025. Google Maps Roads API. https:\/\/developers.google.com\/maps\/documentation\/roads"},{"key":"e_1_3_3_3_50_2","unstructured":"Google. 2025. Google Maps Street View API. https:\/\/developers.google.com\/maps\/documentation\/streetview"},{"key":"e_1_3_3_3_51_2","unstructured":"Google. 2025. Google Street View. https:\/\/www.google.com\/streetview\/"},{"key":"e_1_3_3_3_52_2","unstructured":"Google. 2025. Google Vertex AI. https:\/\/cloud.google.com\/vertex-ai"},{"key":"e_1_3_3_3_53_2","unstructured":"Google. 2025. Supported voices and languages - Google Cloud Text-to-Speech. https:\/\/cloud.google.com\/text-to-speech\/docs\/list-voices-and-types#list_of_all_supported_languages"},{"key":"e_1_3_3_3_54_2","unstructured":"Google. 2025. Treks: Grand Canyon. https:\/\/www.google.com\/maps\/about\/behind-the-scenes\/streetview\/treks\/grand-canyon\/"},{"key":"e_1_3_3_3_55_2","volume-title":"Vertex AI Multimodal Live API","year":"2025","unstructured":"Google. 2025. Vertex AI Multimodal Live API. Google Cloud. https:\/\/cloud.google.com\/vertex-ai\/generative-ai\/docs\/multimodal-live-api"},{"key":"e_1_3_3_3_56_2","unstructured":"Google DeepMind. 2024. Project Astra. https:\/\/deepmind.google\/technologies\/project-astra\/. Accessed: 2025-04-08."},{"key":"e_1_3_3_3_57_2","unstructured":"Google DeepMind. 2025. Gemini model updates: February 2025. https:\/\/blog.google\/technology\/google-deepmind\/gemini-model-updates-february-2025\/"},{"key":"e_1_3_3_3_58_2","unstructured":"Google LLC. 2024. Google Places API: The Place Photo Service. Google Developers Documentation. https:\/\/developers.google.com\/maps\/documentation\/places\/web-service\/photos Accessed: April 9 2025."},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","unstructured":"Christina Granquist Susan\u00a0Y. Sun Sandra\u00a0R. Montezuma Tu\u00a0M. Tran Rachel Gage and Gordon\u00a0E. Legge. 2021. Evaluation and Comparison of Artificial Intelligence Vision Aids: Orcam MyEye 1 and Seeing AI. Journal of Visual Impairment & Blindness 115 4 (2021) 277\u2013285. 10.1177\/0145482X211027492 arXiv:10.1177\/0145482X211027492","DOI":"10.1177\/0145482X211027492"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675658"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/2513383.2513448"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"publisher","unstructured":"Kotaro Hara Shiri Azenkot Megan Campbell Cynthia\u00a0L. Bennett Vicki Le Sean Pannella Robert Moore Kelly Minckler Rochelle\u00a0H. Ng and Jon\u00a0E. Froehlich. 2015. Improving Public Transit Accessibility for Blind Riders by Crowdsourcing Bus Stop Landmark Locations with Google Street View: An Extended Analysis. ACM Trans. Access. Comput. 6 2 Article 5 (March 2015) 23\u00a0pages. 10.1145\/2717513","DOI":"10.1145\/2717513"},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v1i1.13109"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/2642918.2647403"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/1182475.1182492"},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581359"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173772"},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353790"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132525.3132538"},{"key":"e_1_3_3_3_70_2","doi-asserted-by":"publisher","unstructured":"Maryam Hosseini Fabio Miranda Jianzhe Lin and Claudio\u00a0T. Silva. 2022. CitySurfaces: City-scale semantic segmentation of sidewalk materials. Sustainable Cities and Society 79 (2022) 103630. 10.1016\/j.scs.2021.103630","DOI":"10.1016\/j.scs.2021.103630"},{"key":"e_1_3_3_3_71_2","unstructured":"Maryam Hosseini Mikey Saugstad Fabio Miranda Andres Sevtsuk Claudio\u00a0T. Silva and Jon\u00a0E. Froehlich. 2022. Towards Global-Scale Crowd+AI Techniques to Map and Assess Sidewalks for People with Disabilities. arxiv:https:\/\/arXiv.org\/abs\/2206.13677\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2206.13677"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08599-9_13"},{"key":"e_1_3_3_3_73_2","doi-asserted-by":"publisher","unstructured":"Junehyung Jeon and Ayoung Woo. 2023. Deep learning analysis of street panorama images to evaluate the streetscape walkability of neighborhoods for subsidized families in Seoul Korea. Landscape and Urban Planning 230 (2023) 104631. 10.1016\/j.landurbplan.2022.104631","DOI":"10.1016\/j.landurbplan.2022.104631"},{"key":"e_1_3_3_3_74_2","unstructured":"Jianfeng Wu. 2025. VoiceVista. https:\/\/drwjf.github.io\/vvt\/"},{"key":"e_1_3_3_3_75_2","volume-title":"The 4th Annual Workshop on The Future of Urban Accessibility: The Role of AI","author":"Jiang Lucy","year":"2024","unstructured":"Lucy Jiang, Jon\u00a0E. Froehlich, and Leah Findlater. 2024. Making Urban Art Accessible: Current Art Access Techniques, Design Considerations, and the Role of AI. In The 4th Annual Workshop on The Future of Urban Accessibility: The Role of AI (Virtual). 8\u00a0pages."},{"key":"e_1_3_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708359.3712160"},{"key":"e_1_3_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373625.3416995"},{"key":"e_1_3_3_3_78_2","unstructured":"KRDO. 2022. Google\u2019s new Street View camera is more portable and looks weirdly cute. https:\/\/krdo.com\/news\/2022\/05\/24\/googles-new-street-view-camera-is-more-portable-and-looks-weirdly-cute-2\/"},{"key":"e_1_3_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597638.3614481"},{"key":"e_1_3_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501966"},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"publisher","unstructured":"Jiyun Lee Donghyun Kim and Jina Park. 2022. A Machine Learning and Computer Vision Study of the Environmental Characteristics of Streetscapes That Affect Pedestrian Satisfaction. Sustainability 14 9 (2022). 10.3390\/su14095730","DOI":"10.3390\/su14095730"},{"key":"e_1_3_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct64951.2024.00055"},{"key":"e_1_3_3_3_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676449"},{"key":"e_1_3_3_3_84_2","doi-asserted-by":"publisher","DOI":"10.1109\/VIS55277.2024.00020"},{"key":"e_1_3_3_3_85_2","unstructured":"Lit. 2025. Lit: Simple. Fast. Web Components.https:\/\/github.com\/lit\/lit"},{"key":"e_1_3_3_3_86_2","first-page":"34892","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong\u00a0Jae Lee. 2023. Visual Instruction Tuning. In Advances in Neural Information Processing Systems , A.\u00a0Oh, T.\u00a0Naumann, A.\u00a0Globerson, K.\u00a0Saenko, M.\u00a0Hardt, and S.\u00a0Levine (Eds.), Vol.\u00a036. Curran Associates, Inc., 34892\u201334916. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/6dcf277ea32ce3288914faf369fe6de0-Paper-Conference.pdf"},{"key":"e_1_3_3_3_87_2","doi-asserted-by":"publisher","unstructured":"Ali Mansourian and Rachid Oucheikh. 2024. ChatGeoAI: Enabling Geospatial Analysis for Public through Natural Language with Large Language Models. ISPRS International Journal of Geo-Information 13 10 (2024). 10.3390\/ijgi13100348","DOI":"10.3390\/ijgi13100348"},{"key":"e_1_3_3_3_88_2","unstructured":"Mapillary. 2025. About Mapillary. https:\/\/www.mapillary.com\/about"},{"key":"e_1_3_3_3_89_2","doi-asserted-by":"publisher","unstructured":"Keenan\u00a0R. May Brianna\u00a0J. Tomlinson Xiaomeng Ma Phillip Roberts and Bruce\u00a0N. Walker. 2020. Spotlights and Soundscapes: On the Design of Mixed Reality Auditory Environments for Persons with Visual Impairment. ACM Trans. Access. Comput. 13 2 Article 8 (April 2020) 47\u00a0pages. 10.1145\/3378576","DOI":"10.1145\/3378576"},{"key":"e_1_3_3_3_90_2","unstructured":"Meta Platforms Inc.2025. Mapillary by Meta. https:\/\/www.mapillary.com\/"},{"key":"e_1_3_3_3_91_2","volume-title":"Microsoft Soundscape: Empowering people who are blind or have low vision to explore the world around them","year":"2023","unstructured":"Microsoft. 2023. Microsoft Soundscape: Empowering people who are blind or have low vision to explore the world around them. Microsoft. https:\/\/blogs.microsoft.com\/accessibility\/soundscape\/ Microsoft Accessibility Blog."},{"key":"e_1_3_3_3_92_2","unstructured":"Microsoft Corporation. 2025. Bing Streetside. https:\/\/www.bing.com\/maps\/streetside"},{"key":"e_1_3_3_3_93_2","unstructured":"Microsoft Corporation. 2025. Seeing AI. https:\/\/www.microsoft.com\/en-us\/ai\/seeing-ai"},{"key":"e_1_3_3_3_94_2","unstructured":"MIPsoft. 2025. BlindSquare. https:\/\/www.blindsquare.com\/"},{"key":"e_1_3_3_3_95_2","unstructured":"MobX. 2025. MobX: Simple scalable state management. https:\/\/github.com\/mobxjs\/mobx"},{"key":"e_1_3_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct.2019.00122"},{"key":"e_1_3_3_3_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581389"},{"key":"e_1_3_3_3_98_2","unstructured":"Mahjabin Nahar Haeseung Seo Eun-Ju Lee Aiping Xiong and Dongwon Lee. 2024. Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations. arxiv:https:\/\/arXiv.org\/abs\/2404.03745\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2404.03745"},{"key":"e_1_3_3_3_99_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"e_1_3_3_3_100_2","doi-asserted-by":"publisher","unstructured":"Konstantinos Papadopoulos Eleni Koustriava Panagiotis Koukourikos Lefkothea Kartasidou Marialena Barouti Asimis Varveris Marina Misiou Timoclia Zacharogeorga and Theocharis\u00a0Anastasiadis and. 2017. Comparison of three orientation and mobility aids for individuals with blindness: Verbal description audio-tactile map and audio-haptic map. Assistive Technology 29 1 (2017) 1\u20137. 10.1080\/10400435.2016.1171809 arXiv:10.1080\/10400435.2016.1171809 PMID: 27184731.","DOI":"10.1080\/10400435.2016.1171809"},{"key":"e_1_3_3_3_101_2","doi-asserted-by":"publisher","unstructured":"Maria\u00a0Teresa Paratore and Barbara Leporini. 2024. Exploiting the haptic and audio channels to improve orientation and mobility apps for the visually impaired. Universal Access in the Information Society 23 2 (6 2024) 859\u2013869. 10.1007\/s10209-023-00973-4","DOI":"10.1007\/s10209-023-00973-4"},{"key":"e_1_3_3_3_102_2","unstructured":"Jamie Pauls. 2020. Vintage Games Series Part 4: Immerse Yourself in the World of Shades of Doom. https:\/\/www.afb.org\/aw\/21\/12\/17336"},{"key":"e_1_3_3_3_103_2","unstructured":"Joseph Redmon Santosh Divvala Ross Girshick and Ali Farhadi. 2016. You Only Look Once: Unified Real-Time Object Detection. arxiv:https:\/\/arXiv.org\/abs\/1506.02640\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1506.02640"},{"key":"e_1_3_3_3_104_2","doi-asserted-by":"publisher","unstructured":"Samuel Reinders Matthew Butler Ingrid Zukerman Bongshin Lee Lizhen Qu and Kim Marriott. 2025. When Refreshable Tactile Displays Meet Conversational Agents: Investigating Accessible Data Presentation and Analysis with Touch and Speech. IEEE Transactions on Visualization and Computer Graphics 31 1 (2025) 864\u2013874. 10.1109\/TVCG.2024.3456358","DOI":"10.1109\/TVCG.2024.3456358"},{"key":"e_1_3_3_3_105_2","unstructured":"RxJS. 2025. RxJS: Reactive Extensions Library for JavaScript. https:\/\/github.com\/ReactiveX\/rxjs"},{"key":"e_1_3_3_3_106_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353776"},{"key":"e_1_3_3_3_107_2","doi-asserted-by":"publisher","unstructured":"Daisuke Sato Uran Oh Jo\u00e3o Guerreiro Dragan Ahmetovic Kakuya Naito Hironobu Takagi Kris\u00a0M. Kitani and Chieko Asakawa. 2019. NavCog3 in the Wild: Large-scale Blind Indoor Navigation Assistant with Semantic Features. ACM Trans. Access. Comput. 12 3 Article 14 (Aug. 2019) 30\u00a0pages. 10.1145\/3340319","DOI":"10.1145\/3340319"},{"key":"e_1_3_3_3_108_2","doi-asserted-by":"publisher","unstructured":"Joram Schito and Sara Irina\u00a0Fabrikant and. 2018. Exploring maps by sounds: using parameter mapping sonification to make digital elevation models audible. International Journal of Geographical Information Science 32 5 (2018) 874\u2013906. 10.1080\/13658816.2017.1420192 arXiv:10.1080\/13658816.2017.1420192","DOI":"10.1080\/13658816.2017.1420192"},{"key":"e_1_3_3_3_109_2","doi-asserted-by":"publisher","DOI":"10.1109\/HAPTIC.2010.5444631"},{"key":"e_1_3_3_3_110_2","doi-asserted-by":"publisher","DOI":"10.1145\/3517428.3550363"},{"key":"e_1_3_3_3_111_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376353"},{"key":"e_1_3_3_3_112_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300767"},{"key":"e_1_3_3_3_113_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676406"},{"key":"e_1_3_3_3_114_2","doi-asserted-by":"publisher","DOI":"10.1145\/2971648.2971723"},{"key":"e_1_3_3_3_115_2","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk and Andrew M.\u00a0Dai et al.2024. Gemini: A Family of Highly Capable Multimodal Models. arxiv:https:\/\/arXiv.org\/abs\/2312.11805\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2312.11805"},{"key":"e_1_3_3_3_116_2","doi-asserted-by":"publisher","DOI":"10.1145\/1368044.1368066"},{"key":"e_1_3_3_3_117_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30111-0_42"},{"key":"e_1_3_3_3_118_2","doi-asserted-by":"publisher","unstructured":"Bruce\u00a0N. Walker and Jeffrey\u00a0Lindsay and. 2005. Using Virtual Environments to Prototype Auditory Navigation Displays. Assistive Technology 17 1 (2005) 72\u201381. 10.1080\/10400435.2005.10132097 arXiv:10.1080\/10400435.2005.10132097 PMID: 16121647.","DOI":"10.1080\/10400435.2005.10132097"},{"key":"e_1_3_3_3_119_2","doi-asserted-by":"publisher","unstructured":"Bruce\u00a0N. Walker and Jeffrey Lindsay. 2006. Navigation Performance With a Virtual Auditory Display: Effects of Beacon Sound Capture Radius and Practice. Human Factors 48 2 (2006) 265\u2013278. 10.1518\/001872006777724507 arXiv:10.1518\/001872006777724507 PMID: 16884048.","DOI":"10.1518\/001872006777724507"},{"key":"e_1_3_3_3_120_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"e_1_3_3_3_121_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300371"},{"key":"e_1_3_3_3_122_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353798"},{"key":"e_1_3_3_3_123_2","first-page":"95","volume-title":"Proceedings of the 5th International Conference on Disability, Virtual Reality and Associated Technologies, ICDVRAT","volume":"1","author":"Westin Thomas","year":"2004","unstructured":"Thomas Westin. 2004. Game accessibility case study: Terraformers\u2013a real-time 3D graphic game. In Proceedings of the 5th International Conference on Disability, Virtual Reality and Associated Technologies, ICDVRAT , Vol.\u00a01. 95\u2013100. https:\/\/www.researchgate.net\/publication\/260853226_Proceedings_of_the_5th_International_Conference_on_Disability_Virtual_Reality_and_Associated_Technologies_ICDVRAT_2004\/links\/0deec53282e0b15936000000\/Proceedings-of-the-5th-International-Conference-on-Disability-Virtual-Reality-and-Associated-Technologies-ICDVRAT-2004.pdf#page=121"},{"key":"e_1_3_3_3_124_2","doi-asserted-by":"publisher","DOI":"10.1145\/3493612.3520449"},{"key":"e_1_3_3_3_125_2","doi-asserted-by":"publisher","DOI":"10.1145\/2513383.2513449"},{"key":"e_1_3_3_3_126_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2007.4373786"},{"key":"e_1_3_3_3_127_2","volume-title":"Images Tutorial - Web Accessibility Tutorials","author":"(W3C) World Wide Web Consortium","year":"2019","unstructured":"World Wide Web Consortium (W3C). 2019. Images Tutorial - Web Accessibility Tutorials. Web Accessibility Initiative (WAI). https:\/\/www.w3.org\/WAI\/tutorials\/images\/ Part of Web Accessibility Tutorials, providing guidance on how to create websites that meet WCAG."},{"key":"e_1_3_3_3_128_2","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"e_1_3_3_3_129_2","doi-asserted-by":"publisher","unstructured":"Paul\u00a0Bach y Rita Mitchell\u00a0E. Tyler and Kurt\u00a0A. Kaczmarek. 2003. Seeing with the Brain. International Journal of Human\u2013Computer Interaction 15 2 (2003) 285\u2013295. 10.1207\/S15327590IJHC15026","DOI":"10.1207\/S15327590IJHC15026"},{"key":"e_1_3_3_3_130_2","first-page":"21875","volume-title":"Advances in Neural Information Processing Systems","volume":"37","author":"Yang Lihe","year":"2024","unstructured":"Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. 2024. Depth Anything V2. In Advances in Neural Information Processing Systems , A.\u00a0Globerson, L.\u00a0Mackey, D.\u00a0Belgrave, A.\u00a0Fan, U.\u00a0Paquet, J.\u00a0Tomczak, and C.\u00a0Zhang (Eds.), Vol.\u00a037. Curran Associates, Inc., 21875\u201321911. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/26cfdcd8fe6fd75cc53e92963a656c58-Paper-Conference.pdf"},{"key":"e_1_3_3_3_131_2","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2207734"},{"key":"e_1_3_3_3_132_2","unstructured":"Zhangyue Yin Qiushi Sun Qipeng Guo Jiawen Wu Xipeng Qiu and Xuanjing Huang. 2023. Do Large Language Models Know What They Don\u2019t Know? arxiv:https:\/\/arXiv.org\/abs\/2305.18153\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2305.18153"},{"key":"e_1_3_3_3_133_2","doi-asserted-by":"publisher","unstructured":"Limin Zeng Mei Miao and Gerhard Weber. 2014. Interactive Audio-haptic Map Explorer on a Tactile Display. Interacting with Computers 27 4 (02 2014) 413\u2013429. 10.1093\/iwc\/iwu006 arXiv:https:\/\/academic.oup.com\/iwc\/article-pdf\/27\/4\/413\/9644221\/iwu006.pdf","DOI":"10.1093\/iwc\/iwu006"},{"key":"e_1_3_3_3_134_2","doi-asserted-by":"publisher","unstructured":"Haixia Zhao Catherine Plaisant Ben Shneiderman and Jonathan Lazar. 2008. Data Sonification for Users with Visual Impairment: A Case Study with Georeferenced Data. ACM Trans. Comput.-Hum. Interact. 15 1 Article 4 (May 2008) 28\u00a0pages. 10.1145\/1352782.1352786","DOI":"10.1145\/1352782.1352786"},{"key":"e_1_3_3_3_135_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445578"},{"key":"e_1_3_3_3_136_2","doi-asserted-by":"publisher","unstructured":"Kaixing Zhao Rui Lai Bin Guo Le Liu Liang He and Yuhang Zhao. 2024. AI-Vision: A Three-Layer Accessible Image Exploration System for People with Visual Impairments in China. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 8 3 Article 145 (Sept. 2024) 27\u00a0pages. 10.1145\/3678537","DOI":"10.1145\/3678537"},{"key":"e_1_3_3_3_137_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173690"},{"key":"e_1_3_3_3_138_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300341"},{"key":"e_1_3_3_3_139_2","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347906"},{"key":"e_1_3_3_3_140_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"e_1_3_3_3_141_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"}],"event":{"name":"UIST '25: The 38th Annual ACM Symposium on User Interface Software and Technology","location":"Busan Republic of Korea","acronym":"UIST '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746059.3747756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T22:02:15Z","timestamp":1759010535000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746059.3747756"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":140,"alternative-id":["10.1145\/3746059.3747756","10.1145\/3746059"],"URL":"https:\/\/doi.org\/10.1145\/3746059.3747756","relation":{},"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"2025-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}