{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:05:33Z","timestamp":1781006733997,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":130,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3790449","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:33:23Z","timestamp":1776058403000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SceneScout: Towards AI-Driven Access to Street Level Imagery for Blind Users"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9084-9395","authenticated-orcid":false,"given":"Gaurav","family":"Jain","sequence":"first","affiliation":[{"name":"Columbia University, New York, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5619-4452","authenticated-orcid":false,"given":"Leah","family":"Findlater","sequence":"additional","affiliation":[{"name":"Apple Inc., Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8882-3508","authenticated-orcid":false,"given":"Cole","family":"Gleason","sequence":"additional","affiliation":[{"name":"Apple Inc., Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/2468356.2468364"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675631"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2935334.2935361"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2700648.2809847"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675659"},{"key":"e_1_3_3_3_7_2","unstructured":"Apple Inc.2023. VoiceOver. https:\/\/www.apple.com\/accessibility\/vision\/"},{"key":"e_1_3_3_3_8_2","unstructured":"AYES Inc.2023. Oko: The AI-powered Navigation App for People with a Disability. https:\/\/www.ayes.ai\/"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"crossref","unstructured":"Hannah\u00a0M. Badland Simon Opit Karen Witten Robin\u00a0A. Kearns and Suzanne Mavoa. 2010. Can Virtual Streetscape Audits Reliably Replace Physical Streetscape Audits? Journal of Urban Health 87 6 (Dec. 2010) 1007\u20131016.","DOI":"10.1007\/s11524-010-9505-x"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","unstructured":"Jan Balata Zdenek Mikovec Petr Bures and Eva Mulickova. 2016. Automatically Generated Landmark-enhanced Navigation Instructions for Blind Pedestrians. 1605\u20131612. 10.15439\/2016F135","DOI":"10.15439\/2016F135"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2513383.2513445"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445498"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","unstructured":"Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative Research in Psychology 3 2 (Jan. 2006) 77\u2013101. 10.1191\/1478088706qp063oa","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_3_3_15_2","unstructured":"Anke Brock. 2013. Interactive Maps for Visually Impaired People: Design Usability and Spatial Cognition. phdthesis. Universit\u00e9 Toulouse 3 Paul Sabatier."},{"key":"e_1_3_3_3_16_2","unstructured":"Anke Brock. 2013. Interactive Maps for Visually Impaired People: Design Usability and Spatial Cognition. Ph.\u00a0D. Dissertation. Universit\u00e9 Toulouse 3 Paul Sabatier Toulouse France."},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","unstructured":"Anke\u00a0M. Brock Philippe Truillet Bernard Oriola Delphine Picard and Christophe Jouffrais. 2015. Interactivity Improves Usability of Geographic Maps for Visually Impaired People. Human\u2013Computer Interaction 30 2 (2015) 156\u2013194. 10.1080\/07370024.2014.924412","DOI":"10.1080\/07370024.2014.924412"},{"key":"e_1_3_3_3_18_2","series-title":"(NIPS \u201920)","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Brown Tom\u00a0B.","year":"2020","unstructured":"Tom\u00a0B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel\u00a0M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS \u201920). Curran Associates Inc., Red Hook, NY, USA, Article 159, 25\u00a0pages."},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Howard Chen Alane Suhr Dipendra Misra Noah Snavely and Yoav Artzi. 2019. TouchDown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments. 12538\u201312547. https:\/\/openaccess.thecvf.com\/content_CVPR_2019\/html\/Chen_TOUCHDOWN_Natural_Language_Navigation_and_Spatial_Reasoning_in_Visual_Street_CVPR_2019_paper.html","DOI":"10.1109\/CVPR.2019.01282"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614905"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"crossref","unstructured":"Gregory\u00a0D. Clemenson Antonella Maselli Alexander\u00a0J. Fiannaca Amos Miller and Mar Gonzalez-Franco. 2021. Rethinking GPS navigation: creating cognitive maps through auditory clues. Scientific Reports 11 1 (Dec. 2021) 7764.","DOI":"10.1038\/s41598-021-87148-4"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","unstructured":"Laura Cushley Neil Galway and Tunde Peto. 2023. The unseen barriers of the built environment: navigation for people with visual impairment. Town Planning Review 94 1 (2023) 11\u201335. arXiv:https:\/\/www.liverpooluniversitypress.co.uk\/doi\/pdf\/10.3828\/tpr.2022.410.3828\/tpr.2022.4","DOI":"10.3828\/tpr.2022.4"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315103808"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3517428.3550381"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54446-5_17"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"crossref","unstructured":"KA Ericsson and HA Simon. 1980. Verbal Reports as Data. Psychological Review (1980). https:\/\/psycnet.apa.org\/doi\/10.1037\/0033-295X.87.3.215","DOI":"10.1037\/0033-295X.87.3.215"},{"key":"e_1_3_3_3_27_2","unstructured":"L Evett D Brown S Battersby A Ridley and P Smith. 2008. Accessible virtual environments for people who are blind \u2013 creating an intelligent virtual cane using the Nintendo Wii controller. (2008)."},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","unstructured":"Jon\u00a0E. Froehlich Alexander Fiannaca Nimer Jaber Victor Tsara and Shaun Kane. 2025. StreetViewAI: Making Street View Accessible Using Context-Aware Multimodal AI. 10.1145\/3746059.3747756arXiv:https:\/\/arXiv.org\/abs\/2508.08524 [cs].","DOI":"10.1145\/3746059.3747756"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","unstructured":"Rachel Gardner Maya Varma Clare Zhu and Ranjay Krishna. 2020. Determining Question-Answer Plausibility in Crowdsourced Datasets Using Multi-Task Learning. 10.48550\/arXiv.2011.04883arXiv:https:\/\/arXiv.org\/abs\/2011.04883 [cs].","DOI":"10.48550\/arXiv.2011.04883"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"crossref","unstructured":"Reginald G.Golledge R.\u00a0Daniel Jacobson Robert Kitchin and Mark Blades. 2000. Cognitive Maps Spatial Abilities and Human Wayfinding. Geographical review of Japan Series B. 73 2 (2000) 93\u2013104.","DOI":"10.4157\/grj1984b.73.93"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","unstructured":"S. Giraud A.\u00a0M. Brock M.\u00a0J. Mac\u00e9 and C. Jouffrais. 2017. Map Learning with a 3D Printed Interactive Small-Scale Model: Improvement of Space and Text Memorization in Visually Impaired Students. Frontiers in Psychology 8 (June 9 2017) 930. 10.3389\/fpsyg.2017.00930","DOI":"10.3389\/fpsyg.2017.00930"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1002\/9780470379424.ch25"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658933"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"crossref","unstructured":"Cole Gleason Alexander\u00a0J. Fiannaca Melanie Kneisel Edward Cutrell and Meredith\u00a0Ringel Morris. 2018. FootNotes: Geo-referenced Audio Annotations for Nonvisual Exploration. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 2 3 (Sept. 2018) 1\u201324.","DOI":"10.1145\/3264919"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"crossref","unstructured":"Leo\u00a0A. Goodman. 1961. Snowball Sampling. The Annals of Mathematical Statistics 32 1 (1961) 148\u2013170. https:\/\/www.jstor.org\/stable\/2237615 Publisher: Institute of Mathematical Statistics.","DOI":"10.1214\/aoms\/1177705148"},{"key":"e_1_3_3_3_36_2","unstructured":"Google. 2024. Google Maps. https:\/\/www.google.com\/maps"},{"key":"e_1_3_3_3_37_2","unstructured":"Google. 2024. Google Street View. https:\/\/www.google.com\/streetview\/"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132525.3132545"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"crossref","unstructured":"Jo\u00e3o Guerreiro Daisuke Sato Dragan Ahmetovic Eshed Ohn-Bar Kris\u00a0M. Kitani and Chieko Asakawa. 2020. Virtual navigation for blind people: Transferring route knowledge to the real-World. International Journal of Human-Computer Studies 135 (March 2020) 102369.","DOI":"10.1016\/j.ijhcs.2019.102369"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353771"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/2817721.2817743"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","unstructured":"Anisha Gunjal Jihan Yin and Erhan Bas. 2024. Detecting and Preventing Hallucinations in Large Vision Language Models. Proceedings of the AAAI Conference on Artificial Intelligence 38 16 (March 2024) 18135\u201318143. 10.1609\/aaai.v38i16.29771Number: 16.","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"crossref","unstructured":"Danna Gurari Qing Li Abigale\u00a0J. Stangl Anhong Guo Chi Lin Kristen Grauman Jiebo Luo and Jeffrey\u00a0P. Bigham. 2018. VizWiz Grand Challenge: Answering Visual Questions From Blind People. 3608\u20133617. https:\/\/openaccess.thecvf.com\/content_cvpr_2018\/html\/Gurari_VizWiz_Grand_Challenge_CVPR_2018_paper.html","DOI":"10.1109\/CVPR.2018.00380"},{"key":"e_1_3_3_3_44_2","volume-title":"UMD CS PhD Dissertation","author":"Hara Kotaro","year":"2016","unstructured":"Kotaro Hara. 2016. Scalable Methods to Collect and Visualize Sidewalk Accessibility Data for People with Mobility Impairments. In UMD CS PhD Dissertation (College Park, MD). 284\u00a0pages. https:\/\/drum.lib.umd.edu\/handle\/1903\/18992"},{"key":"e_1_3_3_3_45_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 Transactions on Accessible Computing 6 2 (March 2015) 1\u201323. 10.1145\/2717513","DOI":"10.1145\/2717513"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/2642918.2647403"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","unstructured":"J.\u00a0F. Herman T.\u00a0G. Herman and S.\u00a0P. Chatman. 1983. Constructing Cognitive Maps from Partial Information: A Demonstration Study with Congenitally Blind Subjects. Journal of Visual Impairment & Blindness 77 5 (1983) 195\u2013198. 10.1177\/0145482X8307700502","DOI":"10.1177\/0145482X8307700502"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3517428.3544824"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2206.13677"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","unstructured":"Mina Huh Fangyuan Xu Yi-Hao Peng Chongyan Chen Hansika Murugu Danna Gurari Eunsol Choi and Amy Pavel. 2024. Long-Form Answers to Visual Questions from Blind and Low Vision People. 10.48550\/arXiv.2408.06303arXiv:https:\/\/arXiv.org\/abs\/2408.06303 [cs].","DOI":"10.48550\/arXiv.2408.06303"},{"key":"e_1_3_3_3_51_2","unstructured":"Apple Inc.2024. Apple Maps. https:\/\/www.apple.com\/maps\/"},{"key":"e_1_3_3_3_52_2","unstructured":"Apple Inc.2024. Apple Maps Server API. https:\/\/developer.apple.com\/documentation\/applemapsserverapi\/"},{"key":"e_1_3_3_3_53_2","unstructured":"Microsoft Inc.2018. Microsoft Soundscape - Microsoft Research. https:\/\/www.microsoft.com\/en-us\/research\/product\/soundscape\/"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","unstructured":"Koichi Ito Yihan Zhu Mahmoud Abdelrahman Xiucheng Liang Zicheng Fan Yujun Hou Tianhong Zhao Rui Ma Kunihiko Fujiwara Jiani Ouyang Matias Quintana and Filip Biljecki. 2024. ZenSVI: An Open-Source Software for the Integrated Acquisition Processing and Analysis of Street View Imagery Towards Scalable Urban Science. 10.48550\/arXiv.2412.18641arXiv:https:\/\/arXiv.org\/abs\/2412.18641 [cs].","DOI":"10.48550\/arXiv.2412.18641"},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597638.3614498"},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676333"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"publisher","unstructured":"Gaurav Jain Yuanyang Teng Dong\u00a0Heon Cho Yunhao Xing Maryam Aziz and Brian\u00a0A. Smith. 2023. \"I Want to Figure Things Out\": Supporting Exploration in Navigation for People with Visual Impairments. Proc. ACM Hum.-Comput. Interact. 7 CSCW1 Article 63 (April 2023) 28\u00a0pages. 10.1145\/3579496","DOI":"10.1145\/3579496"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","unstructured":"Ziwei Ji Nayeon Lee Rita Frieske Tiezheng Yu Dan Su Yan Xu Etsuko Ishii Ye\u00a0Jin Bang Andrea Madotto and Pascale Fung. 2023. Survey of Hallucination in Natural Language Generation. ACM Comput. Surv. 55 12 (March 2023) 248:1\u2013248:38. 10.1145\/3571730","DOI":"10.1145\/3571730"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025899"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/2982142.2982178"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","unstructured":"Jean Kaddour Joshua Harris Maximilian Mozes Herbie Bradley Roberta Raileanu and Robert McHardy. 2023. Challenges and Applications of Large Language Models. 10.48550\/arXiv.2307.10169arXiv:https:\/\/arXiv.org\/abs\/2307.10169 [cs].","DOI":"10.48550\/arXiv.2307.10169"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373625.3416995"},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047232"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"publisher","unstructured":"Yuka Kaniwa Masaki Kuribayashi Seita Kayukawa Daisuke Sato Hironobu Takagi Chieko Asakawa and Shigeo Morishima. 2024. ChitChatGuide: Conversational Interaction Using Large Language Models for Assisting People with Visual Impairments to Explore a Shopping Mall. Proc. ACM Hum.-Comput. Interact. 8 MHCI (Sept. 2024) 247:1\u2013247:25. 10.1145\/3676492","DOI":"10.1145\/3676492"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"publisher","unstructured":"Hannah\u00a0Rose Kirk Bertie Vidgen Paul R\u00f6ttger and Scott\u00a0A. Hale. 2024. The benefits risks and bounds of personalizing the alignment of large language models to individuals. Nature Machine Intelligence 6 4 (April 2024) 383\u2013392. 10.1038\/s42256-024-00820-y","DOI":"10.1038\/s42256-024-00820-y"},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","unstructured":"R.M. Kitchin and R.D. Jacobson. 1997. Techniques to Collect and Analyze the Cognitive Map Knowledge of Persons with Visual Impairment Or Blindness: Issues of Validity. Journal of Visual Impairment & Blindness 91 4 (July 1997) 360\u2013376. 10.1177\/0145482X9709100405Publisher: SAGE Publications Inc.","DOI":"10.1177\/0145482X9709100405"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3312944"},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"publisher","unstructured":"Masaki Kuribayashi Seita Kayukawa Jayakorn Vongkulbhisal Chieko Asakawa Daisuke Sato Hironobu Takagi and Shigeo Morishima. 2022. Corridor-Walker: Mobile Indoor Walking Assistance for Blind People to Avoid Obstacles and Recognize Intersections. Proc. ACM Hum.-Comput. Interact. 6 MHCI Article 179 (Sept. 2022) 22\u00a0pages. 10.1145\/3546714","DOI":"10.1145\/3546714"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","unstructured":"Orly Lahav Hadas Gedalevitz Steven Battersby David Brown Lindsay Evett and Patrick Merritt. 2018. Virtual environment navigation with look-around mode to explore new real spaces by people who are blind. Disability and Rehabilitation 40 9 (2018) 1072\u20131084. arXiv:https:\/\/doi.org\/10.1080\/09638288.2017.128639110.1080\/09638288.2017.1286391PMID: 28637136.","DOI":"10.1080\/09638288.2017.1286391"},{"key":"e_1_3_3_3_70_2","doi-asserted-by":"publisher","unstructured":"O. Lahav and D. Mioduser. 2008. Haptic-feedback support for cognitive mapping of unknown spaces by people who are blind. International Journal of Human-Computer Studies 66 1 (2008) 23\u201335. 10.1016\/j.ijhcs.2007.08.001","DOI":"10.1016\/j.ijhcs.2007.08.001"},{"key":"e_1_3_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501966"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"publisher","unstructured":"Fabrizio Leo Elena Cocchi and Luca Brayda. 2017. The Effect of Programmable Tactile Displays on Spatial Learning Skills in Children and Adolescents of Different Visual Disability. IEEE Transactions on Neural Systems and Rehabilitation Engineering 25 7 (2017) 861\u2013872. 10.1109\/TNSRE.2016.2619742","DOI":"10.1109\/TNSRE.2016.2619742"},{"key":"e_1_3_3_3_73_2","doi-asserted-by":"publisher","unstructured":"Tomer Levinboim Ashish\u00a0V. Thapliyal Piyush Sharma and Radu Soricut. 2021. Quality Estimation for Image Captions Based on Large-scale Human Evaluations. 10.48550\/arXiv.1909.03396arXiv:https:\/\/arXiv.org\/abs\/1909.03396 [cs].","DOI":"10.48550\/arXiv.1909.03396"},{"key":"e_1_3_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713421"},{"key":"e_1_3_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642089"},{"key":"e_1_3_3_3_76_2","doi-asserted-by":"publisher","unstructured":"Junyi Li Xiaoxue Cheng Wayne\u00a0Xin Zhao Jian-Yun Nie and Ji-Rong Wen. 2023. HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models. 10.48550\/arXiv.2305.11747arXiv:https:\/\/arXiv.org\/abs\/2305.11747 [cs].","DOI":"10.48550\/arXiv.2305.11747"},{"key":"e_1_3_3_3_77_2","doi-asserted-by":"publisher","unstructured":"Xinyu Li Ruiyang Zhou Zachary\u00a0C. Lipton and Liu Leqi. 2024. Personalized Language Modeling from Personalized Human Feedback. 10.48550\/arXiv.2402.05133arXiv:https:\/\/arXiv.org\/abs\/2402.05133 [cs].","DOI":"10.48550\/arXiv.2402.05133"},{"key":"e_1_3_3_3_78_2","doi-asserted-by":"publisher","unstructured":"Yuecheng Liu Dafeng Chi Shiguang Wu Zhanguang Zhang Yaochen Hu Lingfeng Zhang Yingxue Zhang Shuang Wu Tongtong Cao Guowei Huang Helong Huang Guangjian Tian Weichao Qiu Xingyue Quan Jianye Hao and Yuzheng Zhuang. 2025. SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning. 10.48550\/arXiv.2501.10074arXiv:https:\/\/arXiv.org\/abs\/2501.10074 [cs].","DOI":"10.48550\/arXiv.2501.10074"},{"key":"e_1_3_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58805-2_34"},{"key":"e_1_3_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642166"},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025814"},{"key":"e_1_3_3_3_82_2","doi-asserted-by":"crossref","unstructured":"Shachar Maidenbaum Shelly Levy-Tzedek Daniel-Robert Chebat and Amir Amedi. 2013. Increasing Accessibility to the Blind of Virtual Environments Using a Virtual Mobility Aid Based On the \"EyeCane\": Feasibility Study. PLOS ONE 8 8 (08 2013).","DOI":"10.1371\/journal.pone.0072555"},{"key":"e_1_3_3_3_83_2","doi-asserted-by":"publisher","unstructured":"Potsawee Manakul Adian Liusie and Mark J.\u00a0F. Gales. 2023. SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models. 10.48550\/arXiv.2303.08896arXiv:https:\/\/arXiv.org\/abs\/2303.08896 [cs].","DOI":"10.48550\/arXiv.2303.08896"},{"key":"e_1_3_3_3_84_2","doi-asserted-by":"crossref","unstructured":"Sergio Mascetti Dragan Ahmetovic Andrea Gerino and Cristian Bernareggi. 2016. ZebraRecognizer: Pedestrian crossing recognition for people with visual impairment or blindness. Pattern Recognition 60 (Dec. 2016) 405\u2013419.","DOI":"10.1016\/j.patcog.2016.05.002"},{"key":"e_1_3_3_3_85_2","unstructured":"MIPsoft. 2016. BlindSquare. https:\/\/www.blindsquare.com\/"},{"key":"e_1_3_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675658"},{"key":"e_1_3_3_3_87_2","doi-asserted-by":"publisher","DOI":"10.1016\/B0-08-043076-7\/02492-X"},{"key":"e_1_3_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.1016\/B0-08-043076-7\/02492-X"},{"key":"e_1_3_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173633"},{"key":"e_1_3_3_3_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597638.3608395"},{"key":"e_1_3_3_3_91_2","doi-asserted-by":"crossref","unstructured":"Lynn Nadel and Lloyd MacDonald. 1980. Hippocampus: cognitive map or working memory? Behavioral and Neural Biology 29 3 (July 1980) 405\u2013409.","DOI":"10.1016\/S0163-1047(80)90430-6"},{"key":"e_1_3_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581302"},{"key":"e_1_3_3_3_93_2","unstructured":"OpenAI. 2024. GPT-4o. https:\/\/platform.openai.com\/docs\/models#gpt-4o"},{"key":"e_1_3_3_3_94_2","doi-asserted-by":"crossref","unstructured":"Loes Ottink Bram Van\u00a0Raalte Christian\u00a0F. Doeller Thea\u00a0M. Van Der\u00a0Geest and Richard J.\u00a0A. Van\u00a0Wezel. 2022. Cognitive map formation through tactile map navigation in visually impaired and sighted persons. Scientific Reports 12 1 (July 2022) 11567.","DOI":"10.1038\/s41598-022-15858-4"},{"key":"e_1_3_3_3_95_2","doi-asserted-by":"publisher","unstructured":"Konstantinos Papadopoulos Eleni Koustriava and Marialena Barouti. 2017. Cognitive maps of individuals with blindness for familiar and unfamiliar spaces: Construction through audio-tactile maps and walked experience. Computers in Human Behavior 75 (2017) 376\u2013384. 10.1016\/j.chb.2017.04.057","DOI":"10.1016\/j.chb.2017.04.057"},{"key":"e_1_3_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732128"},{"key":"e_1_3_3_3_97_2","doi-asserted-by":"publisher","unstructured":"Lorenzo Picinali Amandine Afonso Michel Denis and Brian\u00a0F.G. Katz. 2014. Exploration of architectural spaces by blind people using auditory virtual reality for the construction of spatial knowledge. International Journal of Human-Computer Studies 72 4 (2014) 393\u2013407. 10.1016\/j.ijhcs.2013.12.008","DOI":"10.1016\/j.ijhcs.2013.12.008"},{"key":"e_1_3_3_3_98_2","first-page":"1032","volume-title":"The Human-Computer Interaction Handbook: Fundamentals, Evolving Technologies and Emerging Applications","author":"Rosson Mary\u00a0Beth","year":"2002","unstructured":"Mary\u00a0Beth Rosson and John\u00a0M. Carroll. 2002. Scenario-Based Design. In The Human-Computer Interaction Handbook: Fundamentals, Evolving Technologies and Emerging Applications. Lawrence Erlbaum Associates, Mahwah, NJ, 1032\u20131050."},{"key":"e_1_3_3_3_99_2","doi-asserted-by":"crossref","unstructured":"Andrew\u00a0G. Rundle Michael D.\u00a0M. Bader Catherine\u00a0A. Richards Kathryn\u00a0M. Neckerman and Julien\u00a0O. Teitler. 2011. Using Google Street View to Audit Neighborhood Environments. American Journal of Preventive Medicine 40 1 (Jan. 2011) 94\u2013100.","DOI":"10.1016\/j.amepre.2010.09.034"},{"key":"e_1_3_3_3_100_2","volume-title":"University of Washington PhD Dissertation","author":"Saha Manaswi","year":"2022","unstructured":"Manaswi Saha. 2022. Designing Interactive Data-Driven Tools for Understanding Urban Accessibility at Scale. In University of Washington PhD Dissertation (Seattle, WA). 299\u00a0pages. https:\/\/orbiscascade-washington.primo.exlibrisgroup.com\/permalink\/01ALLIANCE_UW\/db578v\/cdi_proquest_journals_2736667441"},{"key":"e_1_3_3_3_101_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353776"},{"key":"e_1_3_3_3_102_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300292"},{"key":"e_1_3_3_3_103_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517460"},{"key":"e_1_3_3_3_104_2","doi-asserted-by":"publisher","unstructured":"Alireza Salemi Sheshera Mysore Michael Bendersky and Hamed Zamani. 2024. LaMP: When Large Language Models Meet Personalization. 10.48550\/arXiv.2304.11406arXiv:https:\/\/arXiv.org\/abs\/2304.11406 [cs].","DOI":"10.48550\/arXiv.2304.11406"},{"key":"e_1_3_3_3_105_2","doi-asserted-by":"publisher","DOI":"10.1145\/1878803.1878849"},{"key":"e_1_3_3_3_106_2","doi-asserted-by":"crossref","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 Transactions on Accessible Computing 12 3 (Sept. 2019) 1\u201330.","DOI":"10.1145\/3340319"},{"key":"e_1_3_3_3_107_2","doi-asserted-by":"publisher","unstructured":"Raphael Schumann Wanrong Zhu Weixi Feng Tsu-Jui Fu Stefan Riezler and William\u00a0Yang Wang. 2024. VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View. Proceedings of the AAAI Conference on Artificial Intelligence 38 17 (March 2024) 18924\u201318933. 10.1609\/aaai.v38i17.29858","DOI":"10.1609\/aaai.v38i17.29858"},{"key":"e_1_3_3_3_108_2","doi-asserted-by":"publisher","DOI":"10.1145\/3517428.3544813"},{"key":"e_1_3_3_3_109_2","doi-asserted-by":"publisher","unstructured":"Fatemeh Shiri Xiao-Yu Guo Mona\u00a0Golestan Far Xin Yu Gholamreza Haffari and Yuan-Fang Li. 2024. An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models. 10.48550\/arXiv.2411.06048arXiv:https:\/\/arXiv.org\/abs\/2411.06048 [cs].","DOI":"10.48550\/arXiv.2411.06048"},{"key":"e_1_3_3_3_110_2","doi-asserted-by":"publisher","DOI":"10.1145\/3334480.3375150"},{"key":"e_1_3_3_3_111_2","doi-asserted-by":"publisher","unstructured":"Mark Steyvers Heliodoro Tejeda Aakriti Kumar Catarina Belem Sheer Karny Xinyue Hu Lukas Mayer and Padhraic Smyth. 2025. What Large Language Models Know and What People Think They Know. Nature Machine Intelligence (Jan. 2025). 10.1038\/s42256-024-00976-7arXiv:https:\/\/arXiv.org\/abs\/2401.13835 [cs].","DOI":"10.1038\/s42256-024-00976-7"},{"key":"e_1_3_3_3_112_2","doi-asserted-by":"publisher","DOI":"10.1145\/1851600.1851606"},{"key":"e_1_3_3_3_113_2","doi-asserted-by":"publisher","unstructured":"Zhaoxuan Tan Qingkai Zeng Yijun Tian Zheyuan Liu Bing Yin and Meng Jiang. 2025. Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning. 10.48550\/arXiv.2402.04401arXiv:https:\/\/arXiv.org\/abs\/2402.04401 [cs].","DOI":"10.48550\/arXiv.2402.04401"},{"key":"e_1_3_3_3_114_2","doi-asserted-by":"publisher","DOI":"10.1145\/2982142.2982167"},{"key":"e_1_3_3_3_115_2","first-page":"109","volume-title":"Psychology of Learning and Motivation","author":"Tversky Barbara","year":"1991","unstructured":"Barbara Tversky. 1991. Spatial Mental Models. In Psychology of Learning and Motivation. Vol.\u00a027. Elsevier, 109\u2013145."},{"key":"e_1_3_3_3_116_2","unstructured":"U.S. Access Board. 2025. Traffic Signal Controllers and APS Technologies. https:\/\/www.access-board.gov\/research\/prow\/interfacing-aps\/traffic-signal-controllers-aps-technologies\/. Accessed: 2025-11-28."},{"key":"e_1_3_3_3_117_2","unstructured":"W3C Web Accessibility Initiative (WAI). 2024. Introduction to Web Accessibility. https:\/\/www.w3.org\/WAI\/fundamentals\/accessibility-intro\/"},{"key":"e_1_3_3_3_118_2","unstructured":"W3C Web Accessibility Initiative (WAI). 2024. Tables with Two Headers. https:\/\/www.w3.org\/WAI\/tutorials\/tables\/two-headers\/"},{"key":"e_1_3_3_3_119_2","series-title":"(NIPS \u201922)","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Wei Jason","year":"2024","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed\u00a0H. Chi, Quoc\u00a0V. Le, and Denny Zhou. 2024. Chain-of-thought prompting elicits reasoning in large language models. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS \u201922). Curran Associates Inc., Red Hook, NY, USA, Article 1800, 14\u00a0pages."},{"key":"e_1_3_3_3_120_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353798"},{"key":"e_1_3_3_3_121_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3648641"},{"key":"e_1_3_3_3_122_2","volume-title":"Foundations of orientation and mobility","author":"Wiener William\u00a0R","year":"2010","unstructured":"William\u00a0R Wiener, Richard\u00a0L Welsh, and Bruce\u00a0B Blasch. 2010. Foundations of orientation and mobility. Vol.\u00a01. American Foundation for the Blind."},{"key":"e_1_3_3_3_123_2","doi-asserted-by":"publisher","DOI":"10.1145\/2661334.2661380"},{"key":"e_1_3_3_3_124_2","doi-asserted-by":"publisher","DOI":"10.1145\/2513383.2513449"},{"key":"e_1_3_3_3_125_2","doi-asserted-by":"crossref","unstructured":"Jeffrey\u00a0S. Wilson Cheryl\u00a0M. Kelly Mario Schootman Elizabeth\u00a0A. Baker Aniruddha Banerjee Morgan Clennin and Douglas\u00a0K. Miller. 2012. Assessing the Built Environment Using Omnidirectional Imagery. American Journal of Preventive Medicine 42 2 (Feb. 2012) 193\u2013199.","DOI":"10.1016\/j.amepre.2011.09.029"},{"key":"e_1_3_3_3_126_2","doi-asserted-by":"publisher","unstructured":"Jacob\u00a0O. Wobbrock Shaun\u00a0K. Kane Krzysztof\u00a0Z. Gajos Susumu Harada and Jon Froehlich. 2011. Ability-Based Design: Concept Principles and Examples. ACM Transactions on Accessible Computing 3 3 (April 2011) 1\u201327. 10.1145\/1952383.1952384","DOI":"10.1145\/1952383.1952384"},{"key":"e_1_3_3_3_127_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519729"},{"key":"e_1_3_3_3_128_2","unstructured":"Jihan Yang Runyu Ding Ellis Brown Xiaojuan Qi and Saining Xie. 2024. V-IRL: Grounding Virtual Intelligence in Real Life. http:\/\/arxiv.org\/abs\/2402.03310 arXiv:https:\/\/arXiv.org\/abs\/2402.03310 [cs]."},{"key":"e_1_3_3_3_129_2","doi-asserted-by":"publisher","unstructured":"Jihan Yang Shusheng Yang Anjali\u00a0W. Gupta Rilyn Han Li Fei-Fei and Saining Xie. 2024. Thinking in Space: How Multimodal Large Language Models See Remember and Recall Spaces. 10.48550\/arXiv.2412.14171arXiv:https:\/\/arXiv.org\/abs\/2412.14171 [cs].","DOI":"10.48550\/arXiv.2412.14171"},{"key":"e_1_3_3_3_130_2","doi-asserted-by":"publisher","unstructured":"Yue Zhang Yafu Li Leyang Cui Deng Cai Lemao Liu Tingchen Fu Xinting Huang Enbo Zhao Yu Zhang Yulong Chen Longyue Wang Anh\u00a0Tuan Luu Wei Bi Freda Shi and Shuming Shi. 2023. Siren\u2019s Song in the AI Ocean: A Survey on Hallucination in Large Language Models. 10.48550\/arXiv.2309.01219arXiv:https:\/\/arXiv.org\/abs\/2309.01219 [cs].","DOI":"10.48550\/arXiv.2309.01219"},{"key":"e_1_3_3_3_131_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173690"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3790449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:45:35Z","timestamp":1781005535000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3790449"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":130,"alternative-id":["10.1145\/3772318.3790449","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3790449","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}