{"id":"https://openalex.org/W7138431448","doi":"https://doi.org/10.1145/3796710","title":"Relationship-Experts Transformer for Image Captioning","display_name":"Relationship-Experts Transformer for Image Captioning","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7138431448","doi":"https://doi.org/10.1145/3796710"},"language":"en","primary_location":{"id":"doi:10.1145/3796710","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3796710","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":"https://openalex.org/A5111169554","display_name":"Chuanle Song","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanle Song","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-9893-6195","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129699750","display_name":"Wenjin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjin Huang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8861-4263","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109573014","display_name":"Han Yi Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Jiao","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-2021-8015","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junfeng Li","orcid":"https://orcid.org/0009-0004-8773-7765"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Li","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-8773-7765","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yihua Huang","orcid":"https://orcid.org/0000-0001-6736-7913"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihua Huang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6736-7913","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26552515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"4","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9948999881744385,"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":0.9948999881744385,"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":0.0008999999845400453,"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":0.0005000000237487257,"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":0.9160000085830688},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5554999709129333},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4348999857902527},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41290000081062317},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.39899998903274536},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.3928999900817871},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.39010000228881836},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.38830000162124634},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3303999900817871}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9160000085830688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633999824523926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5687999725341797},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5554999709129333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4505999982357025},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3476000130176544},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C37926939","wikidata":"https://www.wikidata.org/wiki/Q7449061","display_name":"Semantic equivalence","level":4,"score":0.30559998750686646},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3796710","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3796710","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":[{"id":"https://metadata.un.org/sdg/4","score":0.6040158867835999,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5040486816","display_name":null,"funder_award_id":"2022A1515110006 and 2024A1515011259","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6701825051","display_name":null,"funder_award_id":"62276278","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/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2133459682","https://openalex.org/W2302086703","https://openalex.org/W2745461083","https://openalex.org/W2963084599","https://openalex.org/W2990818246","https://openalex.org/W3212847756","https://openalex.org/W4221147537","https://openalex.org/W4226397058","https://openalex.org/W4285186657","https://openalex.org/W4285602612","https://openalex.org/W4312941295","https://openalex.org/W4320487288","https://openalex.org/W4386390772","https://openalex.org/W4388332081","https://openalex.org/W4390195594","https://openalex.org/W4399360161","https://openalex.org/W4400844648","https://openalex.org/W4402327232","https://openalex.org/W4403459022","https://openalex.org/W4406987633","https://openalex.org/W4407272496","https://openalex.org/W4411334357","https://openalex.org/W4414629165"],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1],"is":[2,102],"a":[3,25,51],"cross-modal":[4],"text":[5],"generation":[6],"task":[7],"aimed":[8],"at":[9,204],"understanding":[10],"the":[11,67,95,110,119,122,130,145,150,155,172,190],"relationships":[12],"among":[13],"various":[14],"objects":[15],"in":[16],"an":[17],"image.":[18],"Therefore,":[19],"accurately":[20],"expressing":[21],"object\u2013object":[22],"relations":[23,39,76,170],"remains":[24],"key":[26],"bottleneck":[27],"for":[28],"transformer-based":[29],"image":[30],"captioning.":[31],"Prior":[32],"methods":[33],"usually":[34],"inject":[35],"semantic":[36,73,175,184],"and":[37,41,60,74,86,176,185],"geometric":[38,75,177,186],"once":[40],"keep":[42],"them":[43],"fixed":[44],"while":[45],"only":[46],"updating":[47],"visual":[48,83,124,165],"features,":[49],"creating":[50],"mismatch\u2014evolving":[52],"visuals":[53],"vs.":[54],"frozen":[55],"relations\u2014that":[56],"weakens":[57],"relational":[58],"guidance":[59,173],"leads":[61],"to":[62,104,117,143,161,179],"feature":[63],"entanglement.":[64],"We":[65],"propose":[66],"Relationship-Experts":[68],"Transformer":[69],"(RET),":[70],"which":[71,101,136],"treats":[72],"as":[77],"learnable":[78],"experts":[79,178],"that":[80,194],"guide":[81,118],"object":[82,123,164],"features":[84,125,166],"(students)":[85],"co-evolve":[87],"with":[88,168],"them.":[89],"In":[90],"RET,":[91],"we":[92,128,153],"first":[93],"design":[94,154],"Relationship-Guided":[96],"Feature":[97],"Aggregation":[98],"(RGFA)":[99],"module,":[100,135],"analogous":[103],"experts-guided":[105],"student":[106],"learning,":[107],"specifically":[108],"utilizing":[109],"relationship":[111],"kernel":[112],"(the":[113],"expert\u2019s":[114,146],"knowledge":[115,140],"brain)":[116],"learning":[120],"of":[121,174],"(students).":[126],"Secondly,":[127],"develop":[129],"Experts":[131],"Knowledge":[132,157],"Updating":[133],"(EKU)":[134],"continuously":[137],"iterates":[138],"expert":[139],"during":[141],"training":[142],"enhance":[144],"guiding":[147],"ability":[148],"over":[149],"student.":[151],"Finally,":[152],"Student":[156],"Selector":[158],"(SKS)":[159],"module":[160],"adaptively":[162],"select":[163],"enhanced":[167],"different":[169],"under":[171],"generate":[180],"descriptive":[181],"texts":[182],"embodying":[183],"knowledge.":[187],"Experiments":[188],"on":[189],"MSCOCO":[191],"dataset":[192],"demonstrate":[193],"our":[195],"model":[196],"achieves":[197],"state-of-the-art":[198],"performance.":[199],"All":[200],"codes":[201],"are":[202],"available":[203],"https://github.com/songchuanle-1/RET":[205],".":[206]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}