{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T15:50:24Z","timestamp":1765295424081,"version":"3.37.3"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3314702","type":"journal-article","created":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T17:41:11Z","timestamp":1694626871000},"page":"101167-101182","source":"Crossref","is-referenced-by-count":9,"title":["PerceptGuide: A Perception Driven Assistive Mobility Aid Based on Self-Attention and Multi-Scale Feature Fusion"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5302-2508","authenticated-orcid":false,"given":"Jyoti","family":"Madake","sequence":"first","affiliation":[{"name":"Vishwakarma Institute of Technology, Pune, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8405-9824","authenticated-orcid":false,"given":"Shripad","family":"Bhatlawande","sequence":"additional","affiliation":[{"name":"Vishwakarma Institute of Technology, Pune, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9602-3263","authenticated-orcid":false,"given":"Anjali","family":"Solanke","sequence":"additional","affiliation":[{"name":"Marathwada Mitra Mandal’s College of Engineering, Pune, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1450-2939","authenticated-orcid":false,"given":"Swati","family":"Shilaskar","sequence":"additional","affiliation":[{"name":"Vishwakarma Institute of Technology, Pune, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-020-10197-9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3193097"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09662-3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.03.008"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3131343"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-022-00571-w"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3146828"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2022.3182661"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00202"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-020-00733-8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.06.062"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5236-2"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00146"},{"key":"ref45","article-title":"Contextual attention LSTM networks for sequence-based labeling","author":"li","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref42","article-title":"Neural baby talk: Generating image descriptions from object detections","author":"lu","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref41","article-title":"Conceptual captioning: A human–machine collaborative image captioning framework","author":"zhang","year":"2020","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref44","article-title":"SCAN: Stacked cross attention for image-text matching","author":"li","year":"2019","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref49","first-page":"1987","article-title":"Automatic image captioning","author":"pan","year":"2004","journal-title":"Proc IEEE Int Conf Multimedia Expo (ICME)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09464-7"},{"journal-title":"Envision AI App","year":"0","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/mi12091082"},{"journal-title":"[Online] Available","year":"0","key":"ref4"},{"journal-title":"[Online] Available","year":"0","key":"ref3"},{"key":"ref6","first-page":"1","article-title":"Inclusive mobility solution for visually impaired people using Google cloud vision","author":"gon\u00e7alves","year":"2021","journal-title":"Proc IEEE Int Smart Cities Conf (ISC2)"},{"key":"ref5","first-page":"130e","article-title":"Trends in prevalence of blindness and distance and near vision impairment over 30 years: An analysis for the global burden of disease study","volume":"9","author":"kisa","year":"2020","journal-title":"The Lancet Global Health"},{"key":"ref40","article-title":"Image captioning with global-local attention","author":"chen","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"ref31","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref33","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2015","journal-title":"arXiv 1511 06361"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.130"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S2214-109X(21)00008-5"},{"journal-title":"[Online] Available","year":"0","key":"ref1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00884"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref24","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118669"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13443-5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref29","article-title":"Unifying visualsemantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10250767.pdf?arnumber=10250767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T19:21:20Z","timestamp":1696879280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10250767\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3314702","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}