{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:02:34Z","timestamp":1771952554224,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education","award":["RS-2024-00414053"],"award-info":[{"award-number":["RS-2024-00414053"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3564991","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T17:34:23Z","timestamp":1745861663000},"page":"81933-81947","source":"Crossref","is-referenced-by-count":2,"title":["Human Scene Understanding Mechanism-Based Image Captioning for Blind Assistance"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9964-1411","authenticated-orcid":false,"given":"Jong-Hoon","family":"Kim","sequence":"first","affiliation":[{"name":"Division of Smart Convergence Technology (Multimedia Engineering), Sunchon National University, Suncheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1051-9263","authenticated-orcid":false,"given":"Sung-Wook","family":"Park","sequence":"additional","affiliation":[{"name":"Interdisciplinary Program in IT-Bio Convergence System, Sunchon National University, Suncheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6735-6456","authenticated-orcid":false,"given":"Jun-Ho","family":"Huh","sequence":"additional","affiliation":[{"name":"Department of Data Science, National Korea Maritime and Ocean University, Busan, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1776-9823","authenticated-orcid":false,"given":"Se-Hoon","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Sunchon National University, Suncheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0802-6355","authenticated-orcid":false,"given":"Chun-Bo","family":"Sim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Engineering, Sunchon National University, Suncheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00308"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/i2ct51068.2021.9417907"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/iemtronics52119.2021.9422600"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2920899"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2020.2988435"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3303083"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967258"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1117"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref14","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref15","first-page":"2088","article-title":"Comprehensive assistive mobility system for the visually impaired: The smart blind stick with ultrasonic sensor solution","volume-title":"Proc. Int. Conf. Inventive Comput. Technol. (ICICT)","author":"Illakiya"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.11591\/ijai.v12.i3.pp1104-1117"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSENS.2023.3327565"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-91755-w"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/computers13120305"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/InCACCT61598.2024.10551257"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2023.0140912"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.110057"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1126\/science.1145183"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.7.3.604"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.124.3.372"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1006\/cogp.1999.0728"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2003.09.006"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.31.6.1476"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1167\/7.1.10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3758\/s13415-025-01272-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012375731-9\/50045-8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.94.2.115"},{"key":"ref34","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"He"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref36","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Simonyan"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref40","first-page":"1","article-title":"Transformer network for video to text translation","volume-title":"Proc. Int. Conf. Power, Instrum., Control Comput. (PICC)","author":"Mubashira"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3535321"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3433612"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1103"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref46","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv:2205.14100"},{"key":"ref47","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63830-6_58"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10979381.pdf?arnumber=10979381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T17:46:14Z","timestamp":1747417574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10979381\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3564991","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}