{"id":"https://openalex.org/W7148389292","doi":"https://doi.org/10.1109/access.2026.3679948","title":"DFCap: Zero-Shot Image Captioning With Dynamic Fusion Module","display_name":"DFCap: Zero-Shot Image Captioning With Dynamic Fusion Module","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7148389292","doi":"https://doi.org/10.1109/access.2026.3679948"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3679948","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3679948","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3679948","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086328067","display_name":"Huaming Ran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaming Ran","raw_affiliation_strings":["National Key Laboratory of Complex Aviation System Simulation, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Complex Aviation System Simulation, Chengdu, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021952208","display_name":"Dongzhen Li","orcid":"https://orcid.org/0000-0001-5679-328X"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongzhen Li","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0009-6550-5206","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008607841","display_name":"Wensheng Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wensheng Qiao","raw_affiliation_strings":["National Key Laboratory of Complex Aviation System Simulation, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Complex Aviation System Simulation, Chengdu, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132759055","display_name":"Liliang Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liliang Zhou","raw_affiliation_strings":["National Key Laboratory of Complex Aviation System Simulation, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Complex Aviation System Simulation, Chengdu, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132811618","display_name":"Jing Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Shen","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100681455","display_name":"Haibo Liu","orcid":"https://orcid.org/0000-0003-4837-9956"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Liu","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-4837-9956","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3487397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"51544","last_page":"51557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8528000116348267,"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":0.8528000116348267,"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/T11439","display_name":"Video Analysis and Summarization","score":0.03189999982714653,"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":0.02459999918937683,"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":0.8090000152587891},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.5099999904632568},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.44859999418258667},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41940000653266907},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.3693000078201294},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2928999960422516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163999915122986},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8090000152587891},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6509000062942505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237000226974487},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5099999904632568},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3679948","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3679948","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e8df023c99d142ef98ccc1b11267e99e","is_oa":true,"landing_page_url":"https://doaj.org/article/e8df023c99d142ef98ccc1b11267e99e","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":"IEEE Access, Vol 14, Pp 51544-51557 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3679948","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3679948","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1,44,120],"is":[2,87,100],"a":[3,48,116,123,151,160,166,177,182,187,193],"task":[4],"that":[5,92,205],"generates":[6],"natural":[7,20],"language":[8,21],"descriptions":[9],"for":[10],"visual":[11,74,131],"content":[12],"and":[13,56,75,135,143,165,192,202,213],"connects":[14],"research":[15],"in":[16,39,215],"computer":[17],"vision":[18],"with":[19,122],"processing.While":[22],"supervised":[23],"methods":[24],"have":[25],"achieved":[26,150,176],"significant":[27],"success,":[28],"they":[29],"rely":[30],"heavily":[31],"on":[32,171,200],"large-scale":[33],"annotated":[34],"datasets,":[35],"limiting":[36],"their":[37,98],"applicability":[38],"low-resource":[40],"scenarios.":[41],"Zero-shot":[42],"image":[43,119],"has":[45],"emerged":[46],"as":[47],"promising":[49],"alternative":[50],"by":[51],"leveraging":[52],"pre-trained":[53],"vision-language":[54],"models":[55],"text-only":[57],"training":[58],"to":[59,61,79,88,103],"generalize":[60],"unseen":[62],"images.":[63],"However,":[64],"existing":[65],"approaches":[66],"often":[67],"suffer":[68],"from":[69],"the":[70,104],"modality":[71],"gap":[72],"between":[73],"textual":[76,95,133],"representations,":[77],"leading":[78],"inaccurate":[80],"or":[81],"hallucinated":[82],"content.":[83],"One":[84],"possible":[85],"solution":[86],"introduce":[89],"retrieval-based":[90],"strategies":[91],"incorporate":[93],"external":[94,136],"knowledge,":[96,138],"but":[97],"performance":[99],"highly":[101],"sensitive":[102],"quality":[105],"of":[106,154,158,163,169,180,185,190,196],"retrieved":[107,137,141],"samples.":[108],"To":[109],"address":[110],"these":[111],"challenges,":[112],"we":[113],"propose":[114],"DFCap,":[115],"novel":[117],"zero-shot":[118],"framework":[121],"dynamic":[124],"fusion":[125],"module.":[126],"This":[127],"module":[128],"adaptively":[129],"integrates":[130],"features,":[132,134],"effectively":[139],"reducing":[140],"noise":[142],"enhancing":[144],"caption":[145],"quality.":[146],"The":[147],"proposed":[148],"model":[149],"BLEU-4":[152,178],"score":[153,157,162,168,179,184,189,195],"30.4,":[155],"METEOR":[156,183],"27.0,":[159],"CIDEr":[161,188],"108.0,":[164],"SPICE":[167,194],"20.7":[170],"MSCOCO.":[172],"On":[173],"Flickr30k,":[174],"it":[175],"23.2,":[181],"22.1,":[186],"57.3,":[191],"15.5.":[197],"Extensive":[198],"experiments":[199],"MSCOCO":[201],"Flickr30k":[203],"demonstrate":[204],"DFCap":[206],"achieves":[207],"competitive":[208],"performance,":[209],"validating":[210],"its":[211],"effectiveness":[212],"robustness":[214],"generating":[216],"highquality":[217],"captions":[218],"without":[219],"task-specific":[220],"training.":[221]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-04-03T00:00:00"}
