{"id":"https://openalex.org/W4409882967","doi":"https://doi.org/10.1109/access.2025.3564991","title":"Human Scene Understanding Mechanism-Based Image Captioning for Blind Assistance","display_name":"Human Scene Understanding Mechanism-Based Image Captioning for Blind Assistance","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409882967","doi":"https://doi.org/10.1109/access.2025.3564991"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3564991","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3564991","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3564991","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jong-Hoon Kim","orcid":"https://orcid.org/0000-0001-9964-1411"},"institutions":[{"id":"https://openalex.org/I199143407","display_name":"Sunchon National University","ror":"https://ror.org/043jqrs76","country_code":"KR","type":"education","lineage":["https://openalex.org/I199143407"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong-Hoon Kim","raw_affiliation_strings":["Division of Smart Convergence Technology (Multimedia Engineering), Sunchon National University, Suncheon, Republic of Korea","Ph.D Course of Division of Smart Convergence Technology(Multimedia Engineering), Sunchon National University), Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-9964-1411","affiliations":[{"raw_affiliation_string":"Division of Smart Convergence Technology (Multimedia Engineering), Sunchon National University, Suncheon, Republic of Korea","institution_ids":["https://openalex.org/I199143407"]},{"raw_affiliation_string":"Ph.D Course of Division of Smart Convergence Technology(Multimedia Engineering), Sunchon National University), Republic of Korea","institution_ids":["https://openalex.org/I199143407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564680","display_name":"Sung-Wook Park","orcid":"https://orcid.org/0000-0003-1051-9263"},"institutions":[{"id":"https://openalex.org/I199143407","display_name":"Sunchon National University","ror":"https://ror.org/043jqrs76","country_code":"KR","type":"education","lineage":["https://openalex.org/I199143407"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung-Wook Park","raw_affiliation_strings":["Interdisciplinary Program in IT-Bio Convergence System, Sunchon National University, Suncheon, Republic of Korea","Ph.D Course of Interdisciplinary Program IT-Bio Convergence System, Sunchon National University, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-1051-9263","affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in IT-Bio Convergence System, Sunchon National University, Suncheon, Republic of Korea","institution_ids":["https://openalex.org/I199143407"]},{"raw_affiliation_string":"Ph.D Course of Interdisciplinary Program IT-Bio Convergence System, Sunchon National University, Republic of Korea","institution_ids":["https://openalex.org/I199143407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066063772","display_name":"Jun\u2010Ho Huh","orcid":"https://orcid.org/0000-0001-6735-6456"},"institutions":[{"id":"https://openalex.org/I197867492","display_name":"Korea Maritime and Ocean University","ror":"https://ror.org/01v7y5b55","country_code":"KR","type":"education","lineage":["https://openalex.org/I197867492"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jun-Ho Huh","raw_affiliation_strings":["Department of Data Science, National Korea Maritime and Ocean University, Busan, Republic of Korea","Associate Professor (Tenured) of Dept. of Data Science, (National) Korea Maritime and Ocean University, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-6735-6456","affiliations":[{"raw_affiliation_string":"Department of Data Science, National Korea Maritime and Ocean University, Busan, Republic of Korea","institution_ids":["https://openalex.org/I197867492"]},{"raw_affiliation_string":"Associate Professor (Tenured) of Dept. of Data Science, (National) Korea Maritime and Ocean University, Republic of Korea","institution_ids":["https://openalex.org/I197867492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053786155","display_name":"Se-Hoon Jung","orcid":"https://orcid.org/0000-0002-1776-9823"},"institutions":[{"id":"https://openalex.org/I199143407","display_name":"Sunchon National University","ror":"https://ror.org/043jqrs76","country_code":"KR","type":"education","lineage":["https://openalex.org/I199143407"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Se-Hoon Jung","raw_affiliation_strings":["Department of Computer Engineering, Sunchon National University, Suncheon, Republic of Korea","Associate Professor (Tenure Track) of Department of Computer Engineering, Sunchon National University, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1776-9823","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Sunchon National University, Suncheon, Republic of Korea","institution_ids":["https://openalex.org/I199143407"]},{"raw_affiliation_string":"Associate Professor (Tenure Track) of Department of Computer Engineering, Sunchon National University, Republic of Korea","institution_ids":["https://openalex.org/I199143407"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017207286","display_name":"Chun-Bo Sim","orcid":"https://orcid.org/0000-0003-0802-6355"},"institutions":[{"id":"https://openalex.org/I199143407","display_name":"Sunchon National University","ror":"https://ror.org/043jqrs76","country_code":"KR","type":"education","lineage":["https://openalex.org/I199143407"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chun-Bo Sim","raw_affiliation_strings":["Department of Artificial Intelligence Engineering, Sunchon National University, Suncheon, Republic of Korea","Full Professor (Tenured) of Department of Artificial Intelligence Engineering, Sunchon National University, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-0802-6355","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence Engineering, Sunchon National University, Suncheon, Republic of Korea","institution_ids":["https://openalex.org/I199143407"]},{"raw_affiliation_string":"Full Professor (Tenured) of Department of Artificial Intelligence Engineering, Sunchon National University, Republic of Korea","institution_ids":["https://openalex.org/I199143407"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.8699,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85079327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"13","issue":null,"first_page":"81933","last_page":"81947"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9023681879043579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7521284818649292},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6265895366668701},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6101105213165283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.549331784248352},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5229880809783936}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9023681879043579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7521284818649292},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6265895366668701},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6101105213165283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.549331784248352},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5229880809783936},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3564991","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3564991","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e66d98d4dd854c73a87416763e74318e","is_oa":true,"landing_page_url":"https://doaj.org/article/e66d98d4dd854c73a87416763e74318e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 81933-81947 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3564991","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3564991","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2384921865","display_name":null,"funder_award_id":"RS-2024-00414053","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1566135517","https://openalex.org/W1836465849","https://openalex.org/W1861492603","https://openalex.org/W1973292737","https://openalex.org/W2013112874","https://openalex.org/W2022732461","https://openalex.org/W2056621158","https://openalex.org/W2088112754","https://openalex.org/W2104713750","https://openalex.org/W2130250402","https://openalex.org/W2139501017","https://openalex.org/W2156406284","https://openalex.org/W2194775991","https://openalex.org/W2485261912","https://openalex.org/W2766261529","https://openalex.org/W2950579554","https://openalex.org/W2951390634","https://openalex.org/W2962907269","https://openalex.org/W2962937869","https://openalex.org/W2963446712","https://openalex.org/W2964065937","https://openalex.org/W2964137974","https://openalex.org/W2984862483","https://openalex.org/W2996817764","https://openalex.org/W3019301826","https://openalex.org/W3034221024","https://openalex.org/W3101009614","https://openalex.org/W3120164061","https://openalex.org/W3134971540","https://openalex.org/W3160460845","https://openalex.org/W3161603460","https://openalex.org/W3176425931","https://openalex.org/W4361022410","https://openalex.org/W4387366606","https://openalex.org/W4387935018","https://openalex.org/W4399426516","https://openalex.org/W4399528683","https://openalex.org/W4400975130","https://openalex.org/W4404640582","https://openalex.org/W4406857624","https://openalex.org/W4407063363","https://openalex.org/W4407961693","https://openalex.org/W4408110491","https://openalex.org/W6637373629","https://openalex.org/W6849177959","https://openalex.org/W6850204008"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"This":[0],"study,":[1],"a":[2,19,190],"model":[3,126,151,177],"is":[4,24,88,108],"proposed":[5,125,150,176],"that":[6,123,168],"generates":[7],"descriptive":[8],"sentences":[9],"for":[10,82,111,159,196],"input":[11,71],"images":[12],"visually":[13,161],"impaired":[14],"individuals.":[15],"For":[16],"this":[17],"purpose,":[18],"novel":[20,191],"image":[21,52,60,112,198],"captioning":[22,113],"approach":[23],"introduced,":[25],"integrating":[26],"the":[27,35,51,59,65,73,83,93,96,103,118,124,160,175],"principles":[28,183],"of":[29,68,95,129,132,135,139],"human":[30,55],"visual":[31,56,181],"Understanding":[32],"mechanisms":[33],"with":[34],"Vision":[36,185],"Transformer":[37],"(ViT)":[38],"architecture,":[39],"further":[40,91],"enhanced":[41],"by":[42],"deep":[43],"reinforcement":[44,86],"learning.":[45],"First,":[46],"features":[47,61],"are":[48,62],"extracted":[49],"from":[50],"based":[53],"on":[54,117,171],"perception.":[57],"Second,":[58],"encoded":[63],"through":[64],"encoding":[66],"block":[67],"ViT":[69],"and":[70,137,184,192],"into":[72],"long":[74],"short-term":[75],"memory":[76],"(LSTM)":[77],"network":[78],"to":[79,90,155,165],"generate":[80],"annotations":[81],"image.":[84],"Finally,":[85],"learning":[87],"optimized":[89],"enhance":[92],"accuracy":[94],"generated":[97],"captions.":[98],"Evaluations":[99],"were":[100],"performed":[101],"utilizing":[102],"MSR-VTT":[104,119],"benchmark":[105,120],"dataset,":[106],"which":[107],"widely":[109],"used":[110],"tasks.":[114],"Experimental":[115],"results":[116],"dataset":[121],"demonstrate":[122],"achieves":[127],"BLEU-4":[128],"43.0,":[130],"METEOR":[131],"29.1,":[133],"ROUGE-L":[134],"62.7,":[136],"CIDEr-D":[138],"54.9,":[140],"surpassing":[141],"state-of-the-art":[142],"baseline":[143],"models":[144],"across":[145],"all":[146],"evaluation":[147],"metrics.":[148],"The":[149],"can":[152],"be":[153],"applied":[154],"video":[156],"annotation":[157],"applications":[158],"impaired.":[162],"In":[163],"contrast":[164],"prior":[166],"works":[167],"primarily":[169],"rely":[170],"conventional":[172],"convolutional":[173],"architectures,":[174],"uniquely":[178],"incorporates":[179],"human-inspired":[180],"perception":[182],"Transformer-based":[186],"global":[187],"encoding,":[188],"offering":[189],"interpretable":[193],"framework":[194],"tailored":[195],"assistive":[197],"captioning.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
