{"id":"https://openalex.org/W4417106794","doi":"https://doi.org/10.3390/e27121237","title":"IE-MAS: Internal\u2013External Multi-Agent Steering for Controllable Image Captioning","display_name":"IE-MAS: Internal\u2013External Multi-Agent Steering for Controllable Image Captioning","publication_year":2025,"publication_date":"2025-12-07","ids":{"openalex":"https://openalex.org/W4417106794","doi":"https://doi.org/10.3390/e27121237","pmid":"https://pubmed.ncbi.nlm.nih.gov/41440440"},"language":"en","primary_location":{"id":"doi:10.3390/e27121237","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e27121237","pdf_url":null,"source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"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":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/e27121237","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104170938","display_name":"Tiecheng Cai","orcid":"https://orcid.org/0000-0002-4254-313X"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiecheng Cai","raw_affiliation_strings":["College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408417","display_name":"Chao Chen","orcid":"https://orcid.org/0000-0001-8287-6871"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Chen","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen 518055, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen 518055, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023082310","display_name":"Shian\u2010Jiann Lin","orcid":"https://orcid.org/0000-0003-1550-2743"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshan Lin","raw_affiliation_strings":["College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108904671","display_name":"Sibo Ju","orcid":"https://orcid.org/0009-0008-6131-8449"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sibo Ju","raw_affiliation_strings":["College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003401464","display_name":"Xiangwen Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangwen Liao","raw_affiliation_strings":["College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China","institution_ids":["https://openalex.org/I80947539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003401464"],"corresponding_institution_ids":["https://openalex.org/I80947539"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3940545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"12","first_page":"1237","last_page":"1237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9872000217437744,"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":0.9872000217437744,"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":0.003800000064074993,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8245999813079834},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6424999833106995},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5432999730110168},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5382000207901001},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4869000017642975},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4765999913215637},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4675999879837036},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45320001244544983},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43709999322891235}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8245999813079834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850000262260437},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6424999833106995},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4860999882221222},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41670000553131104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41589999198913574},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3422999978065491},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3005000054836273},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2563000023365021}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/e27121237","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e27121237","pdf_url":null,"source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"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":"Entropy","raw_type":"journal-article"},{"id":"pmid:41440440","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41440440","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":"Entropy (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:80d592d301ee4c27ae3e3d2d80c9190e","is_oa":true,"landing_page_url":"https://doaj.org/article/80d592d301ee4c27ae3e3d2d80c9190e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, Vol 27, Iss 12, p 1237 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12731387","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12731387/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e27121237","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e27121237","pdf_url":null,"source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"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":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8361369946","display_name":null,"funder_award_id":"62476060","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Controllable":[0],"Image":[1],"Captioning":[2],"(CIC)":[3],"aims":[4],"to":[5,17,40,77,91],"generate":[6],"coherent":[7],"and":[8,42,52,84,95,116,122,139,153,173,177],"semantically":[9],"faithful":[10],"textual":[11],"descriptions":[12],"of":[13],"images":[14],"while":[15,109],"adhering":[16],"user-specified":[18],"constraints.":[19],"Existing":[20],"methods":[21],"have":[22],"achieved":[23],"promising":[24],"results":[25,158],"under":[26],"individual":[27],"constraints":[28,45,124],"such":[29],"as":[30,47],"sentimental":[31,175],"style":[32],"or":[33],"sentence":[34],"length.":[35],"However,":[36],"they":[37,129],"typically":[38],"fail":[39],"handle":[41],"satisfy":[43,169],"multiple":[44,164],"simultaneously,":[46],"the":[48,82,106,112,120,170],"controls":[49],"often":[50],"interact":[51],"interfere":[53],"with":[54],"one":[55],"another.":[56],"To":[57],"overcome":[58],"these":[59],"challenges,":[60],"we":[61],"propose":[62],"Internal-External":[63],"Multi-Agent":[64],"Steering":[65],"(IE-MAS)":[66],"for":[67],"CIC.":[68],"IE-MAS":[69,161],"introduces":[70],"an":[71,85,99,143],"internal":[72,150],"multimodal":[73],"steering":[74,145],"(IMS)":[75],"strategy":[76],"control":[78,141,152],"affective":[79,137],"coherence":[80],"within":[81],"caption,":[83],"external":[86,154],"multi-agent":[87],"collaboration":[88],"system":[89],"(EMCS)":[90],"guide":[92],"visual":[93,117],"grounding":[94],"contextual":[96],"alignment.":[97],"From":[98],"information-theoretic":[100],"view,":[101],"IMS":[102],"reduces":[103],"uncertainty":[104],"in":[105],"generation":[107],"process,":[108],"EMCS":[110],"strengthens":[111],"dependency":[113],"between":[114],"captions":[115,167],"inputs,":[118],"converting":[119],"length":[121,140,171],"sentiment":[123],"into":[125],"information":[126],"gains.":[127],"Together,":[128],"produce":[130],"a":[131],"stable":[132],"balance":[133],"among":[134],"semantic":[135],"consistency,":[136],"expression,":[138],"through":[142],"adaptive":[144],"process":[146],"that":[147,160,168],"dynamically":[148],"balances":[149],"linguistic":[151],"perceptual":[155],"grounding.":[156],"Experimental":[157],"demonstrate":[159],"effectively":[162],"coordinates":[163],"constraints,":[165],"producing":[166],"constraint":[172],"are":[174],"expressive":[176],"visually":[178],"faithful.":[179]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-08T00:00:00"}
