{"id":"https://openalex.org/W4392649810","doi":"https://doi.org/10.3390/s24061796","title":"Insights into Object Semantics: Leveraging Transformer Networks for Advanced Image Captioning","display_name":"Insights into Object Semantics: Leveraging Transformer Networks for Advanced Image Captioning","publication_year":2024,"publication_date":"2024-03-11","ids":{"openalex":"https://openalex.org/W4392649810","doi":"https://doi.org/10.3390/s24061796","pmid":"https://pubmed.ncbi.nlm.nih.gov/38544059"},"language":"en","primary_location":{"id":"doi:10.3390/s24061796","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24061796","pdf_url":"https://www.mdpi.com/1424-8220/24/6/1796/pdf?version=1710144303","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/24/6/1796/pdf?version=1710144303","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083952165","display_name":"Deema Abdal Hafeth","orcid":"https://orcid.org/0009-0009-6514-6426"},"institutions":[{"id":"https://openalex.org/I51532219","display_name":"University of Lincoln","ror":"https://ror.org/03yeq9x20","country_code":"GB","type":"education","lineage":["https://openalex.org/I51532219"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Deema Abdal Hafeth","raw_affiliation_strings":["School of Computer Science, University of Lincoln, Lincoln LN6 7TS, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Lincoln, Lincoln LN6 7TS, UK","institution_ids":["https://openalex.org/I51532219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001457450","display_name":"Stefanos Kollias","orcid":"https://orcid.org/0000-0003-2899-0598"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I51532219","display_name":"University of Lincoln","ror":"https://ror.org/03yeq9x20","country_code":"GB","type":"education","lineage":["https://openalex.org/I51532219"]}],"countries":["GB","GR"],"is_corresponding":true,"raw_author_name":"Stefanos Kollias","raw_affiliation_strings":["School of Computer Science, University of Lincoln, Lincoln LN6 7TS, UK","School of Electrical & Computer Engineering, National Technical University of Athens, 15780 Athens, Greece"],"raw_orcid":"https://orcid.org/0000-0003-2899-0598","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Lincoln, Lincoln LN6 7TS, UK","institution_ids":["https://openalex.org/I51532219"]},{"raw_affiliation_string":"School of Electrical & Computer Engineering, National Technical University of Athens, 15780 Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001457450"],"corresponding_institution_ids":["https://openalex.org/I174458059","https://openalex.org/I51532219"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":1.941,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86453116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"24","issue":"6","first_page":"1796","last_page":"1796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9948999881744385,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9925000071525574,"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":0.8393306732177734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8328182697296143},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7454798221588135},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6357133388519287},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5868262648582458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5740393996238708},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5214104652404785},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4994828701019287},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.41723716259002686},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34580957889556885},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33874309062957764},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.327770859003067},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2491230070590973},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08146652579307556}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8393306732177734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8328182697296143},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7454798221588135},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6357133388519287},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5868262648582458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5740393996238708},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5214104652404785},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4994828701019287},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.41723716259002686},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34580957889556885},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33874309062957764},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.327770859003067},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2491230070590973},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08146652579307556},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/s24061796","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24061796","pdf_url":"https://www.mdpi.com/1424-8220/24/6/1796/pdf?version=1710144303","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:38544059","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38544059","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10975165","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10975165","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10975165/pdf/sensors-24-01796.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:65b2b40dada64e5b87c7522129fc9738","is_oa":true,"landing_page_url":"https://doaj.org/article/65b2b40dada64e5b87c7522129fc9738","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":"Sensors, Vol 24, Iss 6, p 1796 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/s24061796","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24061796","pdf_url":"https://www.mdpi.com/1424-8220/24/6/1796/pdf?version=1710144303","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392649810.pdf"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1903029394","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2123301721","https://openalex.org/W2140910804","https://openalex.org/W2157331557","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2508429489","https://openalex.org/W2552161745","https://openalex.org/W2561529111","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2808206191","https://openalex.org/W2886641317","https://openalex.org/W2890531016","https://openalex.org/W2955117135","https://openalex.org/W2963101956","https://openalex.org/W2965597639","https://openalex.org/W2968660381","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3103651098","https://openalex.org/W3126988965","https://openalex.org/W3134428106","https://openalex.org/W3135848044","https://openalex.org/W3138516171","https://openalex.org/W3171155871","https://openalex.org/W3174377922","https://openalex.org/W3175824375","https://openalex.org/W3207136799","https://openalex.org/W3213610319","https://openalex.org/W4281774797","https://openalex.org/W4282962858","https://openalex.org/W4288329833","https://openalex.org/W4304148174","https://openalex.org/W4364856178","https://openalex.org/W4366721356","https://openalex.org/W4376481070","https://openalex.org/W4385245566","https://openalex.org/W4386072307","https://openalex.org/W4387643061","https://openalex.org/W6620707391","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6763643401","https://openalex.org/W6766818547","https://openalex.org/W6770800577","https://openalex.org/W6777254788"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"is":[2,69],"a":[3,16,29,111],"technique":[4],"used":[5],"to":[6,24,39,85,96],"generate":[7,40],"descriptive":[8],"captions":[9],"for":[10],"images.":[11],"Typically,":[12],"it":[13],"involves":[14],"employing":[15],"Convolutional":[17],"Neural":[18,36],"Network":[19],"(CNN)":[20],"as":[21,140],"the":[22,41,44,49,53,71,79,86,94,99,103,141,144,163,169],"encoder":[23,127],"extract":[25],"visual":[26,73,130],"features,":[27],"and":[28,158,171],"decoder":[30,142],"model,":[31],"often":[32],"based":[33],"on":[34,168],"Recurrent":[35],"Networks":[37],"(RNNs),":[38],"captions.":[42,160],"Recently,":[43],"encoder-decoder":[45],"architecture":[46],"has":[47],"witnessed":[48],"widespread":[50],"adoption":[51],"of":[52,88,165,187],"self-attention":[54],"mechanism.":[55],"However,":[56],"this":[57,107],"approach":[58],"faces":[59],"certain":[60],"challenges":[61],"that":[62,70,178],"require":[63],"further":[64],"research.":[65],"One":[66],"such":[67],"challenge":[68],"extracted":[72],"features":[74,131],"do":[75],"not":[76],"fully":[77,97],"exploit":[78],"available":[80],"image":[81,117],"information,":[82],"primarily":[83],"due":[84],"absence":[87],"semantic":[89,119,124],"concepts.":[90,135],"This":[91],"limitation":[92],"restricts":[93],"ability":[95],"comprehend":[98],"content":[100],"depicted":[101],"in":[102,126,143,155,185],"image.":[104],"To":[105],"address":[106],"issue,":[108],"we":[109,137,151],"present":[110],"new":[112],"image-Transformer-based":[113],"model":[114,122,167,180],"boosted":[115],"with":[116,182],"object":[118],"representation.":[120],"Our":[121],"incorporates":[123],"representation":[125],"attention,":[128],"enhancing":[129],"by":[132],"integrating":[133],"instance-level":[134],"Additionally,":[136],"employ":[138],"Transformer":[139],"language":[145],"generation":[146],"module.":[147],"By":[148],"doing":[149],"so,":[150],"achieve":[152],"improved":[153],"performance":[154,164],"generating":[156],"accurate":[157],"diverse":[159],"We":[161],"evaluated":[162],"our":[166,179],"MS-COCO":[170],"novel":[172],"MACE":[173],"datasets.":[174],"The":[175],"results":[176],"illustrate":[177],"aligns":[181],"state-of-the-art":[183],"approaches":[184],"terms":[186],"caption":[188],"generation.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2024-03-12T00:00:00"}