{"id":"https://openalex.org/W4214934429","doi":"https://doi.org/10.1145/3492325","title":"When Pairs Meet Triplets: Improving Low-Resource Captioning via Multi-Objective Optimization","display_name":"When Pairs Meet Triplets: Improving Low-Resource Captioning via Multi-Objective Optimization","publication_year":2022,"publication_date":"2022-03-04","ids":{"openalex":"https://openalex.org/W4214934429","doi":"https://doi.org/10.1145/3492325"},"language":"en","primary_location":{"id":"doi:10.1145/3492325","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3492325","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/A5075742545","display_name":"Yike Wu","orcid":"https://orcid.org/0000-0001-7384-8836"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yike Wu","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052465353","display_name":"Shiwan Zhao","orcid":"https://orcid.org/0000-0001-5068-025X"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwan Zhao","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386145","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-6005-4989"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062064974","display_name":"Xiaojie Yuan","orcid":"https://orcid.org/0000-0002-5876-6856"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Yuan","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010426520","display_name":"Zhong Su","orcid":"https://orcid.org/0000-0003-2303-9787"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Su","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]}],"institutions":[],"countries_distinct_count":1,"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":1,"citation_normalized_percentile":{"value":0.01317732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"18","issue":"3","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":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9922999739646912,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9872999787330627,"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/computer-science","display_name":"Computer science","score":0.8311854600906372},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7841496467590332},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7518145442008972},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.6258970499038696},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5966776013374329},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5589759945869446},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5363138318061829},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5138936042785645},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.485694020986557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46851468086242676},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44383957982063293},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34652575850486755},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24145519733428955}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8311854600906372},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7841496467590332},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7518145442008972},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6258970499038696},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5966776013374329},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5589759945869446},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5363138318061829},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5138936042785645},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.485694020986557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46851468086242676},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44383957982063293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34652575850486755},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24145519733428955},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3492325","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3492325","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/G6459128692","display_name":null,"funder_award_id":"U1903128","funder_id":"https://openalex.org/F4320334063","funder_display_name":"National Natural Science Foundation of China-Xinjiang Joint Fund"}],"funders":[{"id":"https://openalex.org/F4320334063","display_name":"National Natural Science Foundation of China-Xinjiang Joint Fund","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1593271688","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2247931231","https://openalex.org/W2302086703","https://openalex.org/W2418300416","https://openalex.org/W2506483933","https://openalex.org/W2509490957","https://openalex.org/W2547875792","https://openalex.org/W2575842049","https://openalex.org/W2600463316","https://openalex.org/W2661761953","https://openalex.org/W2745461083","https://openalex.org/W2749708282","https://openalex.org/W2758123554","https://openalex.org/W2795151422","https://openalex.org/W2797569913","https://openalex.org/W2890531016","https://openalex.org/W2891965921","https://openalex.org/W2900597592","https://openalex.org/W2963048642","https://openalex.org/W2963084599","https://openalex.org/W2963088515","https://openalex.org/W2963101956","https://openalex.org/W2963909453","https://openalex.org/W2964959218","https://openalex.org/W2966350350","https://openalex.org/W2983141445","https://openalex.org/W2984138079","https://openalex.org/W3034655362","https://openalex.org/W3034984754","https://openalex.org/W3035284526","https://openalex.org/W3102566412","https://openalex.org/W6729448088"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2883671469"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"for":[2],"low-resource":[3,15,23,92,145],"languages":[4],"has":[5],"attracted":[6],"much":[7],"attention":[8,30],"recently.":[9],"Researchers":[10],"propose":[11,185],"to":[12,32,40,53,90,106,143,152,168,186,199,212],"augment":[13],"the":[14,28,34,42,59,73,80,87,91,99,103,110,132,140,144,158,165,169,172,178,181,189,193,201,214,221,227],"caption":[16,77,129],"dataset":[17,112,160],"into":[18,164],"(image,":[19],"rich-resource":[20,81,88,133,141],"language,":[21],"and":[22,26,83,135,161,174,177,203,206],"language)":[24],"triplets":[25,37],"develop":[27],"dual":[29],"mechanism":[31],"exploit":[33],"existence":[35],"of":[36,102,125,131,192],"in":[38,46,79,118,180,195],"training":[39,173,182,202,210,215],"improve":[41],"performance.":[43],"However,":[44],"datasets":[45,78,85,117,163],"triplet":[47,111,159],"form":[48],"are":[49,63],"usually":[50],"small":[51],"due":[52,167],"their":[54],"high":[55],"collecting":[56],"cost.":[57],"On":[58],"other":[60],"hand,":[61],"there":[62],"already":[64],"many":[65],"large-scale":[66,115],"datasets,":[67],"which":[68],"contain":[69],"one":[70,128,136],"pair":[71],"from":[72,86,139,155],"triplet,":[74],"such":[75],"as":[76],"language":[82,89,134,142],"translation":[84,137],"language.":[93,146],"In":[94],"this":[95],"article,":[96],"we":[97],"revisit":[98],"caption-translation":[100,121],"pipeline":[101,122,194],"translation-based":[104],"approach":[105],"utilize":[107],"not":[108,150],"only":[109],"but":[113],"also":[114],"paired":[116,162],"training.":[119],"The":[120],"is":[123,149],"composed":[124],"two":[126,190,208],"models,":[127],"model":[130,138],"Unfortunately,":[147],"it":[148],"trivial":[151],"fully":[153],"benefit":[154],"incorporating":[156],"both":[157],"pipeline,":[166],"gap":[170],"between":[171],"testing":[175,204],"phases":[176],"instability":[179],"process.":[183,216],"We":[184],"jointly":[187],"optimize":[188],"models":[191],"an":[196],"end-to-end":[197],"manner":[198],"bridge":[200],"gap,":[205],"introduce":[207],"auxiliary":[209],"objectives":[211],"stabilize":[213],"Experimental":[217],"results":[218],"show":[219],"that":[220],"proposed":[222],"method":[223],"improves":[224],"significantly":[225],"over":[226],"state-of-the-art":[228],"methods.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}