{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T20:30:36Z","timestamp":1776112236882,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1145\/3663548.3688538","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T18:37:25Z","timestamp":1729449445000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Identifying Crucial Objects in Blind and Low-Vision Individuals' Navigation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6075-2832","authenticated-orcid":false,"given":"Md Touhidul","family":"Islam","sequence":"first","affiliation":[{"name":"College of Information Sciences and Technology, Pennsylvania State University, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8145-9328","authenticated-orcid":false,"given":"Imran","family":"Kabir","sequence":"additional","affiliation":[{"name":"College of Information Sciences and Technology, Pennsylvania State University, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3172-1259","authenticated-orcid":false,"given":"Elena Ariel","family":"Pearce","sequence":"additional","affiliation":[{"name":"College of Arts and Sciences, Drake University, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7692-817X","authenticated-orcid":false,"given":"Md Alimoor","family":"Reza","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Drake University, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5063-3808","authenticated-orcid":false,"given":"Syed Masum","family":"Billah","sequence":"additional","affiliation":[{"name":"College of Information Sciences and Technology, Pennsylvania State University, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. Seeing AI. https:\/\/www.microsoft.com\/en-us\/seeing-ai\/"},{"key":"e_1_3_2_1_2_1","unstructured":"2015. Be My Eyes: Bringing sight to blind and low vision people. https:\/\/www.bemyeyes.com\/"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1070-x"},{"key":"e_1_3_2_1_4_1","volume-title":"Retrieved","year":"2018","unstructured":"Aira. 2018. Aira. https:\/\/aira.io\/. Retrieved May 23, 2020 from https:\/\/aira.io"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the IEEE International Conference on computer vision.","author":"Antol Stanislaw","year":"2015","unstructured":"Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C\u00a0Lawrence Zitnick, and Devi Parikh. 2015. VQA: Visual Question Answering. In Proceedings of the IEEE International Conference on computer vision."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.4324\/9781315680668"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"e_1_3_2_1_12_1","volume-title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. In Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Goyal Yash","year":"2017","unstructured":"Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, and Devi Parikh. 2017. Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_13_1","volume-title":"Towards General Purpose Vision Systems. ArXiv abs\/2104.00743","author":"Gupta Tanmay","year":"2021","unstructured":"Tanmay Gupta, A. Kamath, Aniruddha Kembhavi, and Derek Hoiem. 2021. Towards General Purpose Vision Systems. ArXiv abs\/2104.00743 (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"e_1_3_2_1_15_1","volume-title":"Mask R-CNN. In Proceedings of the IEEE international conference on computer vision (ICCV).","author":"He Kaiming","year":"2017","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1r, and Ross Girshick. 2017. Mask R-CNN. In Proceedings of the IEEE international conference on computer vision (ICCV)."},{"key":"e_1_3_2_1_16_1","unstructured":"Md\u00a0Touhidul Islam Imran Kabir Elena\u00a0Ariel Pearce Md\u00a0Alimoor Reza and Syed\u00a0Masum Billah. 2024. A Dataset for Crucial Object Recognition in Blind and Low-Vision Individuals\u2019 Navigation. arxiv:2407.16777\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2407.16777"},{"key":"e_1_3_2_1_17_1","volume-title":"Lavis: A library for language-vision intelligence. arXiv preprint arXiv:2209.09019","author":"Li Dongxu","year":"2022","unstructured":"Dongxu Li, Junnan Li, Hung Le, Guangsen Wang, Silvio Savarese, and Steven\u00a0CH Hoi. 2022. Lavis: A library for language-vision intelligence. arXiv preprint arXiv:2209.09019 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Machine Learning. PMLR, 12888\u201312900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning. PMLR, 12888\u201312900."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00205"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_21_1","volume-title":"Claiming disability: Knowledge and identity","author":"Linton Simi","unstructured":"Simi Linton. 1998. Claiming disability: Knowledge and identity. NYU Press."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3356727"},{"key":"e_1_3_2_1_23_1","volume-title":"The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes. 2017 IEEE International Conference on Computer Vision (ICCV)","author":"Neuhold Gerhard","year":"2017","unstructured":"Gerhard Neuhold, Tobias Ollmann, Samuel\u00a0Rota Bul\u00f2, and Peter Kontschieder. 2017. The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes. 2017 IEEE International Conference on Computer Vision (ICCV) (2017), 5000\u20135009."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"e_1_3_2_1_25_1","unstructured":"OKO. 2023. OKO makes every intersection accessible. https:\/\/www.ayes.ai\/oko"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445870"},{"key":"e_1_3_2_1_27_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_28_1","volume-title":"Playing for Benchmarks. In IEEE International Conference on Computer Vision, ICCV 2017","author":"Richter R.","year":"2017","unstructured":"Stephan\u00a0R. Richter, Zeeshan Hayder, and Vladlen Koltun. 2017. Playing for Benchmarks. In IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300292"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132525.3134801"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3210825.3213565"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-019-00706-6"},{"key":"e_1_3_2_1_33_1","volume-title":"Change blindness. Trends in cognitive sciences 1, 7","author":"Simons J","year":"1997","unstructured":"Daniel\u00a0J Simons and Daniel\u00a0T Levin. 1997. Change blindness. Trends in cognitive sciences 1, 7 (1997), 261\u2013267."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471225"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445620"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"e_1_3_2_1_37_1","volume-title":"Deep high-resolution representation learning for visual recognition","author":"Wang Jingdong","year":"2020","unstructured":"Jingdong Wang, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Zhao, Dong Liu, Yadong Mu, Mingkui Tan, Xinggang Wang, 2020. Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence 43, 10 (2020), 3349\u20133364."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the 2022 ACM Conference on Information Technology for Social Good. 218\u2013224","author":"Xie Jingyi","year":"2022","unstructured":"Jingyi Xie, Na Li, Sooyeon Lee, and John\u00a0M Carroll. 2022. YouTube Videos as Data: Seeing Daily Challenges for People with Visual Impairments During COVID-19. In Proceedings of the 2022 ACM Conference on Information Technology for Social Good. 218\u2013224."},{"key":"e_1_3_2_1_39_1","volume-title":"Recognize Anything: A Strong Image Tagging Model. arXiv preprint arXiv:2306.03514","author":"Zhang Youcai","year":"2023","unstructured":"Youcai Zhang, Xinyu Huang, Jinyu Ma, Zhaoyang Li, Zhaochuan Luo, Yanchun Xie, Yuzhuo Qin, Tong Luo, Yaqian Li, Shilong Liu, 2023. Recognize Anything: A Strong Image Tagging Model. arXiv preprint arXiv:2306.03514 (2023)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"}],"event":{"name":"ASSETS '24: The 26th International ACM SIGACCESS Conference on Computers and Accessibility","location":"St. John's NL Canada","acronym":"ASSETS '24","sponsor":["SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["The 26th International ACM SIGACCESS Conference on Computers and Accessibility"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3663548.3688538","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:59Z","timestamp":1750294679000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3663548.3688538"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":41,"alternative-id":["10.1145\/3663548.3688538","10.1145\/3663548"],"URL":"https:\/\/doi.org\/10.1145\/3663548.3688538","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2024-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}