{"id":"https://openalex.org/W4400447352","doi":"https://doi.org/10.1109/tcsvt.2024.3425513","title":"Regular Constrained Multimodal Fusion for Image Captioning","display_name":"Regular Constrained Multimodal Fusion for Image Captioning","publication_year":2024,"publication_date":"2024-07-09","ids":{"openalex":"https://openalex.org/W4400447352","doi":"https://doi.org/10.1109/tcsvt.2024.3425513"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3425513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3425513","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","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":"https://openalex.org/A5015410691","display_name":"Liya Wang","orcid":"https://orcid.org/0009-0003-4382-0156"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liya Wang","raw_affiliation_strings":["College of Software, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"College of Software, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100627248","display_name":"Haipeng Chen","orcid":"https://orcid.org/0000-0002-9410-4120"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haipeng Chen","raw_affiliation_strings":["College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102030960","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0003-3023-3027"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089018452","display_name":"Yingda Lyu","orcid":"https://orcid.org/0000-0002-2037-6692"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingda Lyu","raw_affiliation_strings":["Center for Public Education Research, Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"Center for Public Education Research, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015410691"],"corresponding_institution_ids":["https://openalex.org/I194450716"],"apc_list":null,"apc_paid":null,"fwci":1.4928,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83261194,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"34","issue":"11","first_page":"11900","last_page":"11913"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9954000115394592,"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":0.8566610813140869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6833792328834534},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.6570973992347717},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5661382079124451},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5633169412612915},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5298336148262024},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4458179175853729}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8566610813140869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833792328834534},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.6570973992347717},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5661382079124451},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5633169412612915},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5298336148262024},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4458179175853729},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3425513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3425513","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8209437284","display_name":null,"funder_award_id":"62276112","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/F4320322300","display_name":"Jilin University","ror":"https://ror.org/00js3aw79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1987835821","https://openalex.org/W2062955551","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2732016772","https://openalex.org/W2745461083","https://openalex.org/W2798748179","https://openalex.org/W2885013662","https://openalex.org/W2886641317","https://openalex.org/W2887585070","https://openalex.org/W2890531016","https://openalex.org/W2904551248","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963175879","https://openalex.org/W2963952323","https://openalex.org/W2979747405","https://openalex.org/W2984138079","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035463379","https://openalex.org/W3105136412","https://openalex.org/W3106925514","https://openalex.org/W3136792391","https://openalex.org/W3138516171","https://openalex.org/W3175824375","https://openalex.org/W3195680250","https://openalex.org/W3196122027","https://openalex.org/W3203790606","https://openalex.org/W4213453379","https://openalex.org/W4214917601","https://openalex.org/W4221147537","https://openalex.org/W4224261901","https://openalex.org/W4226200183","https://openalex.org/W4283390379","https://openalex.org/W4285186657","https://openalex.org/W4308939443","https://openalex.org/W4312561350","https://openalex.org/W4318035685","https://openalex.org/W4322761295","https://openalex.org/W4327773552","https://openalex.org/W4364297074","https://openalex.org/W4377943811","https://openalex.org/W4385245566","https://openalex.org/W4385638673","https://openalex.org/W4386072307","https://openalex.org/W4390874124","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6638742206","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6763643401"],"related_works":["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","https://openalex.org/W2788731446"],"abstract_inverted_index":{"More":[0],"diverse":[1,220],"and":[2,46,60,94,104,116,134,138,152,161,200,208,221,252],"closer":[3],"to":[4,54,89,131,154,217],"human-like":[5,100],"captions":[6,216],"are":[7],"of":[8,35,43,49,62,70,206,242,248,262],"paramount":[9],"importance":[10],"in":[11,74,246,268],"image":[12,87],"captioning.":[13],"Recent":[14],"research":[15],"has":[16],"achieved":[17],"significant":[18],"advancements,":[19],"with":[20,121,185],"the":[21,33,39,47,58,67,79,157,178,203,214,227,234,239,260],"majority":[22],"adopting":[23],"end-to-end":[24],"encoder-decoder":[25],"architectures":[26],"that":[27],"integrate":[28,91],"specific":[29],"feature-text":[30,44],"processing.":[31],"However,":[32],"homogeneity":[34],"their":[36,209],"model":[37,156],"structures,":[38],"simplicity":[40],"or":[41],"complexity":[42],"fusion,":[45],"uniformity":[48],"training":[50,191],"objectives":[51],"have":[52],"all":[53],"some":[55],"extent":[56],"affected":[57],"diversity":[59],"effectiveness":[61,261],"caption":[63],"generation,":[64],"thus":[65],"limiting":[66],"potential":[68],"applications":[69],"this":[71,75],"task.":[72],"Therefore,":[73],"paper,":[76],"we":[77],"propose":[78],"Regular":[80],"Constrained":[81],"Multimodal":[82],"Fusion":[83],"(RCMF)":[84],"method":[85],"for":[86],"captioning":[88],"better":[90],"information":[92,205],"across":[93],"within":[95],"modalities,":[96],"while":[97],"also":[98],"approaching":[99],"fine-grained":[101,196],"semantic":[102,204],"perception":[103],"relationship":[105],"reasoning":[106,173],"capabilities.":[107],"Initially,":[108],"our":[109,243,263],"RCMF":[110,146,164,264],"preprocesses":[111],"images":[112,199,207],"using":[113],"a":[114,122,148,167,189],"Swin-Transformer":[115],"then":[117],"an":[118],"extended":[119],"encoder":[120],"new":[123,168,190],"intra-modal":[124],"fusion":[125,150,172],"module,":[126],"utilizing":[127],"window-focused":[128],"linear":[129],"attention":[130],"capture":[132],"features":[133],"leveraging":[135],"refined":[136],"grid":[137],"global":[139],"visual":[140],"features.":[141],"By":[142],"combining":[143],"text":[144,160],"features,":[145],"employs":[147],"cross-modal":[149],"module":[151],"decoder":[153],"deeply":[155],"interaction":[158],"between":[159,198],"image.":[162],"Additionally,":[163],"first":[165],"introduces":[166],"additional":[169],"regulatory":[170],"modal":[171],"(MFR)":[174],"branch,":[175],"which":[176],"surpasses":[177],"above":[179],"architectures.":[180],"Its":[181],"MFR":[182],"loss":[183,187],"combined":[184],"cross-entropy":[186],"forms":[188],"objective":[192],"strategy,":[193],"effectively":[194],"mining":[195],"relationships":[197],"text,":[201],"perceiving":[202],"corresponding":[210],"captions,":[211],"thereby":[212],"regulating":[213],"generated":[215],"be":[218],"more":[219],"human-like.":[222],"Experimental":[223],"results":[224,256],"based":[225],"on":[226],"MS":[228],"COCO":[229],"2014":[230],"dataset,":[231],"particularly":[232],"under":[233],"same":[235],"experimental":[236],"conditions,":[237],"demonstrate":[238],"outstanding":[240],"performance":[241],"method,":[244],"especially":[245],"terms":[247],"METEOR,":[249],"ROUGE-L,":[250],"CIDEr,":[251],"SPICE":[253],"metrics.":[254],"Visualization":[255],"further":[257],"intuitively":[258],"confirm":[259],"method.":[265],"Source":[266],"code":[267],"<uri":[269],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[270],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/200084/RCMF-for-image-caption</uri>.":[271]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}