{"id":"https://openalex.org/W4399639661","doi":"https://doi.org/10.3390/s24123820","title":"Explicit Image Caption Reasoning: Generating Accurate and Informative Captions for Complex Scenes with LMM","display_name":"Explicit Image Caption Reasoning: Generating Accurate and Informative Captions for Complex Scenes with LMM","publication_year":2024,"publication_date":"2024-06-13","ids":{"openalex":"https://openalex.org/W4399639661","doi":"https://doi.org/10.3390/s24123820","pmid":"https://pubmed.ncbi.nlm.nih.gov/38931605"},"language":"en","primary_location":{"id":"doi:10.3390/s24123820","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24123820","pdf_url":"https://www.mdpi.com/1424-8220/24/12/3820/pdf?version=1718270452","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/1424-8220/24/12/3820/pdf?version=1718270452","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061730458","display_name":"Mingzhang Cui","orcid":"https://orcid.org/0009-0000-9299-9752"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingzhang Cui","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China"],"raw_orcid":"https://orcid.org/0009-0000-9299-9752","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087826107","display_name":"Caihong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Caihong Li","raw_affiliation_strings":["Key Laboratory of Artificial Intelligence and Computing Power Technology, Lanzhou 730000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Artificial Intelligence and Computing Power Technology, Lanzhou 730000, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100317379","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-9575-2330"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China","institution_ids":["https://openalex.org/I76214153"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087826107"],"corresponding_institution_ids":[],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.6952,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69317558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"24","issue":"12","first_page":"3820","last_page":"3820"},"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":0.9747999906539917,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9639000296592712,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9226582050323486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7987841367721558},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7301760315895081},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7107251882553101},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6121894717216492},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4280424118041992},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4136055111885071},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39297547936439514},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32780909538269043}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9226582050323486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7987841367721558},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7301760315895081},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7107251882553101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6121894717216492},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4280424118041992},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4136055111885071},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39297547936439514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32780909538269043},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/s24123820","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24123820","pdf_url":"https://www.mdpi.com/1424-8220/24/12/3820/pdf?version=1718270452","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:38931605","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38931605","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:11207553","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11207553","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11207553/pdf/sensors-24-03820.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:47ba9da4981f4aa48da59147eec6d7da","is_oa":false,"landing_page_url":"https://doaj.org/article/47ba9da4981f4aa48da59147eec6d7da","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 24, Iss 12, p 3820 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/s24123820","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24123820","pdf_url":"https://www.mdpi.com/1424-8220/24/12/3820/pdf?version=1718270452","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399639661.pdf"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2064458142","https://openalex.org/W2081388731","https://openalex.org/W2101105183","https://openalex.org/W2108373063","https://openalex.org/W2109802560","https://openalex.org/W2127672659","https://openalex.org/W2133459682","https://openalex.org/W2156422881","https://openalex.org/W2251613956","https://openalex.org/W2251654079","https://openalex.org/W2506483933","https://openalex.org/W2534253848","https://openalex.org/W2552002300","https://openalex.org/W2575842049","https://openalex.org/W2605243085","https://openalex.org/W2607151106","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2808206191","https://openalex.org/W2949376505","https://openalex.org/W2949806279","https://openalex.org/W2962937869","https://openalex.org/W2963138277","https://openalex.org/W2963658612","https://openalex.org/W2963686907","https://openalex.org/W2963693848","https://openalex.org/W2963743213","https://openalex.org/W2963758027","https://openalex.org/W2970429618","https://openalex.org/W2970744242","https://openalex.org/W2976658881","https://openalex.org/W2979987972","https://openalex.org/W2997248215","https://openalex.org/W3034316193","https://openalex.org/W3034655362","https://openalex.org/W3035323998","https://openalex.org/W3103022576","https://openalex.org/W3104814493","https://openalex.org/W3110019360","https://openalex.org/W3160190143","https://openalex.org/W4224917636","https://openalex.org/W4225323055","https://openalex.org/W4313024519","https://openalex.org/W4318718936","https://openalex.org/W4366330503","https://openalex.org/W4376312115","https://openalex.org/W4386566533","https://openalex.org/W6682631176","https://openalex.org/W6683199212","https://openalex.org/W6742263385","https://openalex.org/W6743895910","https://openalex.org/W6810334672","https://openalex.org/W6851592950","https://openalex.org/W6853116092"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,14,96],"sensor":[4,117,144],"technologies":[5],"and":[6,32,56,79,111,140],"deep":[7],"learning":[8],"has":[9],"significantly":[10],"advanced":[11,64],"the":[12,30,90,97,121,133],"field":[13],"image":[15,22],"captioning,":[16],"especially":[17],"for":[18,59],"complex":[19,36,60],"scenes.":[20,37],"Traditional":[21],"captioning":[23],"methods":[24],"are":[25],"often":[26],"unable":[27],"to":[28,72,81],"handle":[29],"intricacies":[31],"detailed":[33],"relationships":[34,78],"within":[35],"To":[38],"overcome":[39],"these":[40],"limitations,":[41],"this":[42],"paper":[43],"introduces":[44],"Explicit":[45,122],"Image":[46,123],"Caption":[47,124],"Reasoning":[48,125],"(ECR),":[49],"a":[50,94],"novel":[51],"approach":[52],"that":[53],"generates":[54],"accurate":[55],"informative":[57],"captions":[58],"scenes":[61],"captured":[62],"by":[63,114,129],"sensors.":[65],"ECR":[66,88],"employs":[67],"an":[68],"enhanced":[69],"inference":[70,103],"chain":[71,104],"analyze":[73],"sensor-derived":[74],"images,":[75],"examining":[76],"object":[77],"interactions":[80],"achieve":[82],"deeper":[83],"semantic":[84],"understanding.":[85],"We":[86,119],"implement":[87],"using":[89],"optimized":[91],"ICICD":[92,134],"dataset,":[93],"subset":[95],"sensor-oriented":[98],"Flickr30K-EE":[99],"dataset":[100,107],"containing":[101],"comprehensive":[102],"information.":[105],"This":[106],"enhances":[108],"training":[109],"efficiency":[110],"caption":[112],"quality":[113],"leveraging":[115],"rich":[116],"data.":[118],"create":[120],"Multimodal":[126],"Model":[127],"(ECRMM)":[128],"fine-tuning":[130],"TinyLLaVA":[131],"with":[132],"dataset.":[135],"Experiments":[136],"demonstrate":[137],"ECR's":[138],"effectiveness":[139],"robustness":[141],"in":[142],"processing":[143],"data,":[145],"outperforming":[146],"traditional":[147],"methods.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}