{"id":"https://openalex.org/W4416415737","doi":"https://doi.org/10.1145/3776746","title":"Enhancing Image Captioning through Bridging Image-Text Gap and Reducing Hallucinations","display_name":"Enhancing Image Captioning through Bridging Image-Text Gap and Reducing Hallucinations","publication_year":2025,"publication_date":"2025-11-20","ids":{"openalex":"https://openalex.org/W4416415737","doi":"https://doi.org/10.1145/3776746"},"language":"en","primary_location":{"id":"doi:10.1145/3776746","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776746","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhihao Wang","orcid":"https://orcid.org/0009-0004-9246-2735"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","Tianjin University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0004-9246-2735","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]},{"raw_affiliation_string":"Tianjin University of Technology, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406150","display_name":"Feifei Zhang","orcid":"https://orcid.org/0000-0002-8153-9977"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feifei Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","Tianjin University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-8153-9977","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]},{"raw_affiliation_string":"Tianjin University of Technology, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082673764","display_name":"Lingkai Ran","orcid":"https://orcid.org/0009-0002-6481-7338"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingkai Ran","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","Tianjin University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0002-6481-7338","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]},{"raw_affiliation_string":"Tianjin University of Technology, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Caixia Song","orcid":"https://orcid.org/0009-0003-3455-2508"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caixia Song","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","Tianjin University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0003-3455-2508","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]},{"raw_affiliation_string":"Tianjin University of Technology, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100643788","display_name":"Ling Zhou","orcid":"https://orcid.org/0000-0002-8313-5749"},"institutions":[{"id":"https://openalex.org/I111950717","display_name":"Macau University of Science and Technology","ror":"https://ror.org/03jqs2n27","country_code":"MO","type":"education","lineage":["https://openalex.org/I111950717","https://openalex.org/I4391767947"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Ling Zhou","raw_affiliation_strings":["Macau University of Science and Technology, Macao, China","Macau University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-8313-5749","affiliations":[{"raw_affiliation_string":"Macau University of Science and Technology, Macao, China","institution_ids":["https://openalex.org/I111950717"]},{"raw_affiliation_string":"Macau University of Science and Technology, China","institution_ids":["https://openalex.org/I111950717"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31266969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"1","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9764999747276306,"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":0.9764999747276306,"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":0.010599999688565731,"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/T10028","display_name":"Topic Modeling","score":0.0015999999595806003,"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":0.8852999806404114},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.8651000261306763},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6074000000953674},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5924999713897705},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.5216000080108643},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4544000029563904},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45249998569488525},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44609999656677246}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8852999806404114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8815000057220459},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8651000261306763},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6074000000953674},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5924999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5781000256538391},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5216000080108643},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4494999945163727},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.375900000333786},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2777999937534332}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3776746","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776746","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2877084605","display_name":null,"funder_award_id":"22JCYBJC00030, 24JCJQJC00190","funder_id":"https://openalex.org/F4320323993","funder_display_name":"Natural Science Foundation of Tianjin City"},{"id":"https://openalex.org/G3625633375","display_name":null,"funder_award_id":"62376196, 62036012, U23A20387, 62106262, 62202331, 62206200, and 62276118","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323993","display_name":"Natural Science Foundation of Tianjin City","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2506483933","https://openalex.org/W3015199478","https://openalex.org/W3217412301","https://openalex.org/W4281560470","https://openalex.org/W4313476584","https://openalex.org/W4317435799","https://openalex.org/W4405056178"],"related_works":[],"abstract_inverted_index":{"While":[0],"autoregressive":[1],"models":[2],"have":[3],"achieved":[4],"remarkable":[5],"success":[6],"in":[7,17,80],"image":[8,182,207],"captioning,":[9],"their":[10,15],"slow":[11],"inference":[12],"speed":[13],"limits":[14],"applicability":[16],"real-time":[18],"scenarios.":[19],"Non-autoregressive":[20],"methods":[21],"provide":[22],"a":[23],"promising":[24],"alternative":[25],"for":[26,48],"faster":[27],"caption":[28],"generation;":[29],"however,":[30],"they":[31,38],"still":[32],"encounter":[33],"significant":[34],"challenges.":[35],"In":[36],"particular,":[37],"struggle":[39],"to":[40,69,132,150,222],"capture":[41],"complex":[42,130],"content":[43],"and":[44,52,99,129,157],"abstract":[45],"concepts":[46],"necessary":[47],"producing":[49],"semantically":[50,180],"rich":[51,181],"accurate":[53],"captions,":[54,183],"which":[55,103,118,146],"hinders":[56],"the":[57,60,64,85,95,113,134,141,154,160,177,186,204,211,218],"bridging":[58],"of":[59,105,162,179,188,215],"image\u2013text":[61],"gap.":[62,136],"Moreover,":[63],"generation":[65],"process":[66],"often":[67],"leads":[68],"object":[70],"hallucination\u2014instances":[71],"where":[72],"incorrect":[73],"or":[74],"non-existent":[75],"objects":[76],"are":[77],"described,":[78],"resulting":[79],"captions":[81,126],"that":[82,172,198],"misalign":[83],"with":[84,127],"actual":[86],"visual":[87,120,148],"content.":[88],"To":[89],"address":[90],"these":[91],"issues,":[92],"we":[93],"propose":[94],"Vision-Text":[96],"Semantic":[97],"Reconstruction":[98,115],"Contrast":[100],"(VTSRC)":[101],"mechanism,":[102],"consists":[104],"two":[106],"key":[107],"modules.":[108],"The":[109,137],"first":[110],"module":[111,139],"is":[112,140],"Visual-Text":[114],"Network":[116],"(VRN),":[117],"reconstructs":[119],"representations":[121],"into":[122],"textual":[123],"space,":[124],"enriching":[125],"contributive":[128],"semantics":[131],"bridge":[133],"image-text":[135],"second":[138],"Visual":[142],"Contrastive":[143],"Generation":[144],"(VCG),":[145],"leverages":[147],"uncertainty":[149],"contrast":[151],"distributions,":[152],"recalibrating":[153],"model\u2019s":[155],"output":[156],"significantly":[158],"reducing":[159,185],"incidence":[161],"hallucination,":[163],"thereby":[164],"generating":[165],"coherent":[166],"linguistic":[167],"representations.":[168],"Extensive":[169],"evaluations":[170],"demonstrate":[171,197],"our":[173],"approach":[174],"markedly":[175],"improves":[176],"creation":[178],"considerably":[184],"frequency":[187],"hallucinations":[189],"while":[190],"maintaining":[191],"high":[192],"descriptive":[193],"accuracy.":[194],"Experimental":[195],"results":[196],"VTSRC":[199],"achieves":[200],"competitive":[201],"performance":[202],"on":[203,217],"challenging":[205],"MSCOCO":[206],"captioning":[208],"dataset,":[209],"reaching":[210],"best":[212],"CIDEr":[213],"score":[214],"133.9%":[216],"COCO-caption":[219],"Karpathy":[220],"split":[221],"date.":[223]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-20T00:00:00"}
