{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T00:56:04Z","timestamp":1768006564536,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T00:00:00Z","timestamp":1792627200000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2318101"],"award-info":[{"award-number":["2318101"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,26]]},"DOI":"10.1145\/3663547.3759726","type":"proceedings-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T16:29:36Z","timestamp":1761150576000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["NaviSense: A Multimodal Assistive Mobile application for Object Retrieval by Persons with Visual Impairment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6497-0433","authenticated-orcid":false,"given":"Ajay Narayanan","family":"Sridhar","sequence":"first","affiliation":[{"name":"The Pennsylvania State University, University Park, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1880-187X","authenticated-orcid":false,"given":"Fuli","family":"Qiao","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, University Park, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5312-6860","authenticated-orcid":false,"given":"Nelson Daniel","family":"Troncoso Aldas","sequence":"additional","affiliation":[{"name":"Independent Researcher, Stanford, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7427-455X","authenticated-orcid":false,"given":"Yanpei","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2679-6679","authenticated-orcid":false,"given":"Mehrdad","family":"Mahdavi","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, University Park, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0168-2977","authenticated-orcid":false,"given":"Laurent","family":"Itti","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6266-6068","authenticated-orcid":false,"given":"Vijaykrishnan","family":"Narayanan","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, University Park, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,22]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/2935334.2935361"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376143"},{"key":"e_1_3_3_1_4_2","unstructured":"Moondream AI. 2025. Moondream VLM. https:\/\/moondream.ai\/ Accessed: 2025-04-15."},{"key":"e_1_3_3_1_5_2","unstructured":"AiPoly. n. d.. Vision AI for the Blind and Visually Impaired. https:\/\/www.aipoly.com\/ Accessed on 04.16.2025."},{"key":"e_1_3_3_1_6_2","unstructured":"Aira. 2025. Aira: Visual interpretation services for the blind and low vision. https:\/\/aira.io\/ Accessed on 04.10.2025."},{"key":"e_1_3_3_1_7_2","unstructured":"Arthur Benton and Daniel Tranel. 1993. Visuoperceptual visuospatial and visuoconstructive disorders. (1993)."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/PHT.2013.6461334"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543821"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Jacky Cao Kit-Yung Lam Lik-Hang Lee Xiaoli Liu Pan Hui and Xiang Su. 2023. Mobile augmented reality: User interfaces frameworks and intelligence. Comput. Surveys 55 9 (2023) 1\u201336.","DOI":"10.1145\/3557999"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3027063.3049786"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676375"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC.2018.8407319"},{"key":"e_1_3_3_1_14_2","unstructured":"A2\u00a0Milk Company. 2025. A2 Milk Products. https:\/\/www.a2milk.com\/ Accessed: 2025-04-15."},{"key":"e_1_3_3_1_15_2","unstructured":"Cottonelle. 2025. Cottonelle Products. https:\/\/www.cottonelle.com\/en-us\/ Accessed: 2025-04-15."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69057-3_112"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Francesco Di\u00a0Stefano Stefano Chiappini Alban Gorreja Mattia Balestra and Roberto Pierdicca. 2021. Mobile 3D scan LiDAR: A literature review. Geomatics natural hazards and risk 12 1 (2021) 2387\u20132429.","DOI":"10.1080\/19475705.2021.1964617"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/1414471.1414529"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Ping-Jung Duh Yu-Cheng Sung Liang-Yu\u00a0Fan Chiang Yung-Ju Chang and Kuan-Wen Chen. 2020. V-eye: A vision-based navigation system for the visually impaired. IEEE Transactions on Multimedia 23 (2020) 1567\u20131580.","DOI":"10.1109\/TMM.2020.3001500"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Fatma El-Zahraa El-Taher Luis Miralles-Pechu\u00e1n Jane Courtney Kristina Millar Chantelle Smith and Susan McKeever. 2023. A survey on outdoor navigation applications for people with visual impairments. IEEE Access 11 (2023) 14647\u201314666.","DOI":"10.1109\/ACCESS.2023.3244073"},{"key":"e_1_3_3_1_21_2","unstructured":"Be\u00a0My Eyes. 2023. Introducing: Be My AI. https:\/\/www.bemyeyes.com\/blog\/introducing-be-my-ai\/ Blog post published August 7 2023. Accessed: 2025\u201106\u201115."},{"key":"e_1_3_3_1_22_2","unstructured":"Be\u00a0My Eyes. 2025. Be My Eyes: Helping the blind and visually impaired. https:\/\/www.bemyeyes.com Accessed: 2025-04-10."},{"key":"e_1_3_3_1_23_2","unstructured":"Google. 2025. Gemini Live with camera and screen sharing is now free on Android and iOS. https:\/\/blog.google\/products\/gemini\/gemini-app-updates-io-2025\/#gemini-live Blog post published May 20 2025. Accessed: 2025\u201106\u201115."},{"key":"e_1_3_3_1_24_2","unstructured":"Great Value. 2025. Great Value Products. https:\/\/www.walmart.com\/cp\/great-value\/3495493 Accessed: 2025-04-15."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676391"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Samantha Horvath John Galeotti Bing Wu Roberta Klatzky Mel Siegel and George Stetten. 2014. FingerSight: Fingertip haptic sensing of the visual environment. IEEE journal of translational engineering in health and medicine 2 (2014) 1\u20139.","DOI":"10.1109\/JTEHM.2014.2309343"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Xuhui Hu Aiguo Song Zhikai Wei and Hong Zeng. 2022. StereoPilot: A wearable target location system for blind and visually impaired using spatial audio rendering. IEEE Transactions on Neural Systems and Rehabilitation Engineering 30 (2022) 1621\u20131630.","DOI":"10.1109\/TNSRE.2022.3182661"},{"key":"e_1_3_3_1_28_2","unstructured":"Apple Inc.2025. ARKit. https:\/\/developer.apple.com\/documentation\/arkit Accessed: 2025-06-23."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/HAPTICS52432.2022.9765618"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Kibum Kim Xiangshi Ren Seungmoon Choi and Hong\u00a0Z Tan. 2016. Assisting people with visual impairments in aiming at a target on a large wall-mounted display. International Journal of Human-Computer Studies 86 (2016) 109\u2013120.","DOI":"10.1016\/j.ijhcs.2015.10.002"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713788"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501966"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Sooyeon Lee Nelson Daniel\u00a0Troncoso Aldas Chonghan Lee Mary\u00a0Beth Rosson John\u00a0M Carroll and Vijaykrishnan Narayanan. 2022. AIGuide: augmented reality hand guidance in a visual prosthetic. ACM Transactions on Accessible Computing (TACCESS) 15 2 (2022) 1\u201332.","DOI":"10.1145\/3508501"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132525.3134817"},{"key":"e_1_3_3_1_35_2","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong\u00a0Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems 36 (2023) 34892\u201334916."},{"key":"e_1_3_3_1_36_2","unstructured":"Ruiping Liu Jiaming Zhang Angela Sch\u00f6n Karin M\u00fcller Junwei Zheng Kailun Yang Anhong Guo Kathrin Gerling and Rainer Stiefelhagen. 2025. ObjectFinder: An Open-Vocabulary Assistive System for Interactive Object Search by Blind People. arxiv:https:\/\/arXiv.org\/abs\/2412.03118\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2412.03118"},{"key":"e_1_3_3_1_37_2","first-page":"38","volume-title":"European Conference on Computer Vision","author":"Liu Shilong","year":"2024","unstructured":"Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, et\u00a0al. 2024. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In European Conference on Computer Vision. Springer, 38\u201355."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Andrea Lubin and Devajyoti Deka. 2012. Role of public transportation as job access mode: Lessons from survey of people with disabilities in New Jersey. Transportation research record 2277 1 (2012) 90\u201397.","DOI":"10.3141\/2277-11"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557328"},{"key":"e_1_3_3_1_40_2","unstructured":"Martin\u2019s Snacks. 2025. Martin\u2019s Sour cream & Onions Potato Chips. https:\/\/martinssnacks.com\/product\/martins-sour-cream-onion-potato-chips\/ Accessed: 2025-04-15."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713486"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Alex McClimens Nick Partridge and Ed Sexton. 2014. How do people with learning disability experience the city centre? A Sheffield case study. Health & place 28 (2014) 14\u201321.","DOI":"10.1016\/j.healthplace.2014.02.014"},{"key":"e_1_3_3_1_43_2","unstructured":"Microsoft. 2025. Seeing AI: Your personal AI assistant for the blind. https:\/\/www.microsoft.com\/en-us\/seeing-ai Accessed: 2025-04-10."},{"key":"e_1_3_3_1_44_2","unstructured":"Matthias Minderer Alexey Gritsenko and Neil Houlsby. 2023. Scaling open-vocabulary object detection. Advances in Neural Information Processing Systems 36 (2023) 72983\u201373007."},{"key":"e_1_3_3_1_45_2","unstructured":"OpenAI. 2024. Advanced Voice mode rolling out to ChatGPT Plus and Team users. https:\/\/x.com\/OpenAI\/status\/1838642444365369814 Tweet posted on September 24 2024. Accessed: 2025\u201106\u201115."},{"key":"e_1_3_3_1_46_2","unstructured":"OpenAI. 2025. GPT-4o-mini: OpenAI\u2019s compact language model. https:\/\/www.openai.com\/gpt-4o-mini Accessed: 2025-04-10."},{"key":"e_1_3_3_1_47_2","unstructured":"OpenAI. 2025. Introducing the Realtime API. https:\/\/openai.com\/index\/introducing-the-realtime-api\/ Accessed: 2025-04-10."},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23771-3_47"},{"key":"e_1_3_3_1_49_2","unstructured":"Pompeian. 2025. Pompeian Mild-Tase Olive Oil. https:\/\/pompeian.com\/product\/mild-taste-olive-oil\/ Accessed: 2025-04-15."},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581415"},{"key":"e_1_3_3_1_51_2","unstructured":"Ray-Ban. 2025. Ray-Ban Meta AI Glasses. https:\/\/www.ray-ban.com\/usa\/ray-ban-meta-ai-glasses Accessed on 04.10.2025."},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2014.6961320"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"crossref","unstructured":"Lee Stearns Ruofei Du Uran Oh Catherine Jou Leah Findlater David\u00a0A Ross and Jon\u00a0E Froehlich. 2016. Evaluating haptic and auditory directional guidance to assist blind people in reading printed text using finger-mounted cameras. ACM Transactions on Accessible Computing (TACCESS) 9 1 (2016) 1\u201338.","DOI":"10.1145\/2914793"},{"key":"e_1_3_3_1_54_2","unstructured":"Austin Stone Ted Xiao Yao Lu Keerthana Gopalakrishnan Kuang-Huei Lee Quan Vuong Paul Wohlhart Sean Kirmani Brianna Zitkovich Fei Xia et\u00a0al. 2023. Open-world object manipulation using pre-trained vision-language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.00905 (2023)."},{"key":"e_1_3_3_1_55_2","unstructured":"TapTapSee. n. d.. TapTapSee: Visual recognition app for the blind and visually impaired. https:\/\/taptapseeapp.com\/ Accessed on 04.10.2025."},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16199-0_45"},{"key":"e_1_3_3_1_57_2","unstructured":"Tide. 2025. Tide Detergent Products. https:\/\/tide.com\/en-us Accessed: 2025-04-15."},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"crossref","unstructured":"Greg Townley Bret Kloos and Patricia\u00a0A Wright. 2009. Understanding the experience of place: Expanding methods to conceptualize and measure community integration of persons with serious mental illness. Health & place 15 2 (2009) 520\u2013531.","DOI":"10.1016\/j.healthplace.2008.08.011"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373625.3417028"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3648641"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/1866218.1866244"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3532106.3533560"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/FMSys62467.2024.00010"},{"key":"e_1_3_3_1_64_2","unstructured":"Weihao Yu Zhengyuan Yang Linjie Li Jianfeng Wang Kevin Lin Zicheng Liu Xinchao Wang and Lijuan Wang. 2023. Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.02490 (2023)."},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"crossref","unstructured":"John\u00a0S Zelek Sam Bromley Daniel Asmar and David Thompson. 2003. A haptic glove as a tactile-vision sensory substitution for wayfinding. Journal of Visual Impairment & Blindness 97 10 (2003) 621\u2013632.","DOI":"10.1177\/0145482X0309701007"},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3688828.3699636"},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"crossref","unstructured":"Jingyi Zhang Jiaxing Huang Sheng Jin and Shijian Lu. 2024. Vision-language models for vision tasks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024).","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_3_1_68_2","unstructured":"Xizhou Zhu Weijie Su Lewei Lu Bin Li Xiaogang Wang and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.04159 (2020)."}],"event":{"name":"ASSETS '25: The 27th International ACM SIGACCESS Conference on Computers and Accessibility","location":"Denver Colorado USA","acronym":"ASSETS '25","sponsor":["SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3663547.3759726","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3663547.3759726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T17:50:20Z","timestamp":1767981020000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3663547.3759726"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":67,"alternative-id":["10.1145\/3663547.3759726","10.1145\/3663547"],"URL":"https:\/\/doi.org\/10.1145\/3663547.3759726","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]},"assertion":[{"value":"2025-10-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}