{"id":"https://openalex.org/W7117457605","doi":"https://doi.org/10.1007/s10791-025-09839-0","title":"Enhanced image captioning with advanced context-aware object relational model","display_name":"Enhanced image captioning with advanced context-aware object relational model","publication_year":2025,"publication_date":"2025-12-29","ids":{"openalex":"https://openalex.org/W7117457605","doi":"https://doi.org/10.1007/s10791-025-09839-0"},"language":"en","primary_location":{"id":"doi:10.1007/s10791-025-09839-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-025-09839-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-025-09839-0.pdf","source":{"id":"https://openalex.org/S5407036663","display_name":"Discover Computing","issn_l":"2948-2992","issn":["2948-2992"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s10791-025-09839-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104268025","display_name":"Madhvi Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I91277730","display_name":"Maulana Azad National Institute of Technology","ror":"https://ror.org/026vtd268","country_code":"IN","type":"education","lineage":["https://openalex.org/I91277730"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Madhvi Patel","raw_affiliation_strings":["Department of Computer Science, Maulana Azad National Institute of Technology, Bhopal, 462003, Madhya Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Maulana Azad National Institute of Technology, Bhopal, 462003, Madhya Pradesh, India","institution_ids":["https://openalex.org/I91277730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121516389","display_name":"Pranay Deepak Reddy Vaka","orcid":null},"institutions":[{"id":"https://openalex.org/I91277730","display_name":"Maulana Azad National Institute of Technology","ror":"https://ror.org/026vtd268","country_code":"IN","type":"education","lineage":["https://openalex.org/I91277730"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pranay Deepak Reddy Vaka","raw_affiliation_strings":["Centre for Artificial Intelligence, Maulana Azad National Institute of Technology, Bhopal, 462003, Madhya Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence, Maulana Azad National Institute of Technology, Bhopal, 462003, Madhya Pradesh, India","institution_ids":["https://openalex.org/I91277730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054880944","display_name":"Dhirendra Pratap Singh","orcid":"https://orcid.org/0000-0001-5519-3928"},"institutions":[{"id":"https://openalex.org/I91277730","display_name":"Maulana Azad National Institute of Technology","ror":"https://ror.org/026vtd268","country_code":"IN","type":"education","lineage":["https://openalex.org/I91277730"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dhirendra Pratap Singh","raw_affiliation_strings":["Department of Computer Science, Maulana Azad National Institute of Technology, Bhopal, 462003, Madhya Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Maulana Azad National Institute of Technology, Bhopal, 462003, Madhya Pradesh, India","institution_ids":["https://openalex.org/I91277730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032170911","display_name":"Jaytrilok Choudhary","orcid":"https://orcid.org/0000-0002-8200-7403"},"institutions":[{"id":"https://openalex.org/I91277730","display_name":"Maulana Azad National Institute of Technology","ror":"https://ror.org/026vtd268","country_code":"IN","type":"education","lineage":["https://openalex.org/I91277730"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jaytrilok Choudhary","raw_affiliation_strings":["Department of Computer Science, Maulana Azad National Institute of Technology, Bhopal, 462003, Madhya Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Maulana Azad National Institute of Technology, Bhopal, 462003, Madhya Pradesh, India","institution_ids":["https://openalex.org/I91277730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121518431","display_name":"Surendra Solanki","orcid":null},"institutions":[{"id":"https://openalex.org/I99552915","display_name":"University of Rajasthan","ror":"https://ror.org/05arfhc56","country_code":"IN","type":"education","lineage":["https://openalex.org/I99552915"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Surendra Solanki","raw_affiliation_strings":["Department of Artificial Intelligence and Machine Learning, Manipal University Jaipur, Jaipur, 303007, Rajasthan, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence and Machine Learning, Manipal University Jaipur, Jaipur, 303007, Rajasthan, India","institution_ids":["https://openalex.org/I99552915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5121518431"],"corresponding_institution_ids":["https://openalex.org/I99552915"],"apc_list":null,"apc_paid":null,"fwci":1.1177,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8116983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"28","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9941999912261963,"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":0.9941999912261963,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0006000000284984708,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0006000000284984708,"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":0.9757000207901001},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5688999891281128},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5422999858856201},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5288000106811523},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.515999972820282},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48809999227523804},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47909998893737793}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9757000207901001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6295999884605408},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5950000286102295},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5422999858856201},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3797999918460846},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34389999508857727},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10791-025-09839-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-025-09839-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-025-09839-0.pdf","source":{"id":"https://openalex.org/S5407036663","display_name":"Discover Computing","issn_l":"2948-2992","issn":["2948-2992"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:04abae7b5b4b4045be7228252871b98a","is_oa":true,"landing_page_url":"https://doaj.org/article/04abae7b5b4b4045be7228252871b98a","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":"Discover Computing, Vol 28, Iss 1, Pp 1-27 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s10791-025-09839-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-025-09839-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-025-09839-0.pdf","source":{"id":"https://openalex.org/S5407036663","display_name":"Discover Computing","issn_l":"2948-2992","issn":["2948-2992"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.45260360836982727,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7117457605.pdf","grobid_xml":"https://content.openalex.org/works/W7117457605.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W1897761818","https://openalex.org/W1969616664","https://openalex.org/W2105103432","https://openalex.org/W2116341502","https://openalex.org/W2157331557","https://openalex.org/W2296385829","https://openalex.org/W2463955103","https://openalex.org/W2481240925","https://openalex.org/W2508429489","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2750690203","https://openalex.org/W2766261529","https://openalex.org/W2776212699","https://openalex.org/W2962949934","https://openalex.org/W2963277143","https://openalex.org/W2963686907","https://openalex.org/W2964253311","https://openalex.org/W2988823324","https://openalex.org/W2991252721","https://openalex.org/W3091588028","https://openalex.org/W3093225449","https://openalex.org/W3093686763","https://openalex.org/W3107503524","https://openalex.org/W3129050402","https://openalex.org/W3173220247","https://openalex.org/W3203790606","https://openalex.org/W4283722434","https://openalex.org/W4283793362","https://openalex.org/W4285723986","https://openalex.org/W4286221672","https://openalex.org/W4289654392","https://openalex.org/W4293066072","https://openalex.org/W4304080274","https://openalex.org/W4307106676","https://openalex.org/W4310447809","https://openalex.org/W4312320490","https://openalex.org/W4312922092","https://openalex.org/W4319309602","https://openalex.org/W4322760880","https://openalex.org/W4323341874","https://openalex.org/W4366123788","https://openalex.org/W4386903087","https://openalex.org/W4387193636","https://openalex.org/W4389947181","https://openalex.org/W4391320510","https://openalex.org/W4395004920","https://openalex.org/W4399050644","https://openalex.org/W4400810498","https://openalex.org/W4402177968","https://openalex.org/W4403864329","https://openalex.org/W4406754683","https://openalex.org/W4406755126","https://openalex.org/W4407860211","https://openalex.org/W4407932368","https://openalex.org/W4409103248","https://openalex.org/W4409762655","https://openalex.org/W4409919258","https://openalex.org/W4410252926","https://openalex.org/W4410342812","https://openalex.org/W4410958471","https://openalex.org/W4412408017","https://openalex.org/W4412954572","https://openalex.org/W4413114556","https://openalex.org/W6960165482"],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1,26,34],"generates":[2],"text":[3],"in":[4,14,41,67,148],"natural":[5],"language":[6],"to":[7,28,96,113],"describe":[8],"a":[9,73],"given":[10],"image.":[11,69],"Recent":[12],"advances":[13],"various":[15,65],"object":[16],"detection":[17],"with":[18,110,124],"attention":[19,112],"mechanisms":[20],"pushed":[21],"for":[22,61,104],"exploring":[23],"multiple":[24],"image":[25,55,88,105],"methodologies":[27],"create":[29],"more":[30],"meaningful":[31],"and":[32,107,131,146,155,167,171,176],"accurate":[33],"models.":[35],"Although":[36],"existing":[37],"pipelines":[38],"do":[39],"well":[40],"describing":[42],"the":[43,121,179],"image,":[44],"there":[45],"has":[46],"not":[47,82],"been":[48],"enough":[49],"emphasis":[50],"on":[51,152,165,169,178],"relationship":[52,85],"modeling":[53,58,86],"between":[54,64,87],"features.":[56],"Relationship":[57],"is":[59],"crucial":[60],"establishing":[62],"context":[63],"objects":[66],"an":[68],"We":[70,119],"have":[71],"proposed":[72,122],"novel":[74],"Advanced":[75],"Context-Aware":[76],"Object":[77],"Relational":[78],"Model":[79],"(ACAORM)":[80],"that":[81,136],"only":[83],"improves":[84],"features":[89],"but":[90],"also":[91],"better":[92],"sentence":[93],"generation":[94],"due":[95],"Transformer":[97],"architecture.":[98],"ACAORM":[99,142],"builds":[100,108],"relation-aware":[101],"visual":[102],"representations":[103],"description":[106],"captions":[109],"prior":[111],"relevant":[114],"Regions":[115],"of":[116],"Interest":[117],"(RoI).":[118],"tested":[120],"methodology":[123],"three":[125],"widely":[126],"used":[127],"datasets,":[128],"Flickr8K,":[129],"Flickr30K,":[130],"MS-COCO.":[132],"The":[133],"results":[134],"show":[135],"it":[137],"beats":[138],"numerous":[139],"cutting-edge":[140,160],"techniques.":[141],"scores":[143],"0.3526,":[144],"0.4439,":[145],"0.8813":[147],"$$":[149,151],"BLEU-4":[150],"Flickr8k,":[153],"Flickr30k":[154,170],"MS-COCO,":[156],"respectively,":[157],"outperforming":[158],"popular":[159],"models":[161],"such":[162],"as":[163],"VitaCap":[164],"Flickr8k":[166],"AGF":[168],"MS-COCO":[172],"by":[173],"10.88%,":[174],"47.96%":[175],"139.48%":[177],"respective":[180],"benchmarks.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-12-29T00:00:00"}