{"id":"https://openalex.org/W3186513731","doi":"https://doi.org/10.1145/3447685","title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","display_name":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","publication_year":2021,"publication_date":"2021-07-20","ids":{"openalex":"https://openalex.org/W3186513731","doi":"https://doi.org/10.1145/3447685","mag":"3186513731"},"language":"en","primary_location":{"id":"doi:10.1145/3447685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447685","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"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 Knowledge Discovery from Data","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/A5100632772","display_name":"Fenglin Liu","orcid":"https://orcid.org/0000-0001-7715-5228"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fenglin Liu","raw_affiliation_strings":["ADSPLAB, School of ECE, Peking University, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352418","display_name":"Xian Wu","orcid":"https://orcid.org/0000-0003-1118-9710"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Wu","raw_affiliation_strings":["Tencent, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018805166","display_name":"Shen Ge","orcid":"https://orcid.org/0000-0001-8992-1006"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shen Ge","raw_affiliation_strings":["Tencent, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049239373","display_name":"Xuancheng Ren","orcid":"https://orcid.org/0000-0002-6994-2114"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuancheng Ren","raw_affiliation_strings":["MOE Key Laboratory of Computational Linguistics, School of EECS, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Computational Linguistics, School of EECS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380499","display_name":"Wei Fan","orcid":"https://orcid.org/0000-0002-0342-6272"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Fan","raw_affiliation_strings":["Tencent, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101441137","display_name":"Xu Sun","orcid":"https://orcid.org/0000-0001-8241-9320"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Sun","raw_affiliation_strings":["School of EECS, Peking University and Center for Data Science, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of EECS, Peking University and Center for Data Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["ADSPLAB, School of ECE, Peking University and Peng Cheng Laboratory, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University and Peng Cheng Laboratory, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100632772"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.6725,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71052288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"16","issue":"1","first_page":"1","last_page":"19"},"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":0.9957000017166138,"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/T10028","display_name":"Topic Modeling","score":0.9864000082015991,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7716299891471863},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6892051100730896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5668155550956726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.551336407661438},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5352597236633301},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5030750632286072},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45356887578964233},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44652464985847473},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23336493968963623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716299891471863},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6892051100730896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5668155550956726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.551336407661438},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5352597236633301},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5030750632286072},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45356887578964233},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44652464985847473},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23336493968963623},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447685","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"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 Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2110485445","https://openalex.org/W2150824314","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2552161745","https://openalex.org/W2745461083","https://openalex.org/W2885013662","https://openalex.org/W2886641317","https://openalex.org/W2887585070","https://openalex.org/W2888321701","https://openalex.org/W2890531016","https://openalex.org/W2953486038","https://openalex.org/W2963033554","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2964018924","https://openalex.org/W2968101724","https://openalex.org/W2970869018","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W2997591391","https://openalex.org/W2998356391","https://openalex.org/W3035485997","https://openalex.org/W3093374703","https://openalex.org/W3098605233","https://openalex.org/W3100995281","https://openalex.org/W3101703188","https://openalex.org/W3104152799","https://openalex.org/W3105136412","https://openalex.org/W3106784008","https://openalex.org/W3116651605","https://openalex.org/W3168640669"],"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/W3009270862","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"Vision-and-language":[0],"(V-L)":[1],"tasks":[2,198,205,213],"require":[3],"the":[4,49,59,68,110,121,132,152,155,185,245,256,262],"system":[5],"to":[6,37,135,150,235,240],"understand":[7],"both":[8,53,203],"vision":[9,20,54,106,124],"content":[10],"and":[11,21,41,55,107,109,125,174,208,211,254,261],"natural":[12],"language,":[13,108],"thus":[14,115],"learning":[15],"fine-grained":[16],"joint":[17],"representations":[18,40,71,111],"of":[19,27,62,112,165,258],"language":[22,56,126,172,176],"(a.k.a.":[23],"V-L":[24,33,39,70,233],"representations)":[25],"is":[26,96,181],"paramount":[28],"importance.":[29],"Recently,":[30],"various":[31],"pre-trained":[32,232],"models":[34,51,234],"are":[35,72],"proposed":[36,217],"learn":[38],"achieve":[42],"improved":[43],"results":[44],"in":[45,74,127,141],"many":[46],"tasks.":[47,187],"However,":[48],"mainstream":[50],"process":[52],"inputs":[57],"with":[58],"same":[60],"set":[61],"attention":[63,103],"matrices.":[64],"As":[65],"a":[66,97,162,241,251],"result,":[67],"generated":[69],"entangled":[73],"one":[75],"common":[76],"latent":[77],"space":[78],".":[79],"To":[80,119],"tackle":[81],"this":[82,145],"problem,":[83],"we":[84,130,249],"propose":[85],"DiMBERT":[86,136,160,180,191],"(short":[87,219],"for":[88,105,184,220],"Di":[89,221],"sentangled":[90,222],"M":[91,223],"ultimodal-Attention":[92],"BERT":[93],"),":[94],"which":[95,137],"novel":[98],"framework":[99],"that":[100,190],"applies":[101],"separated":[102],"spaces":[104],"multi-modalities":[113],"can":[114,226],"be":[116,227],"disentangled":[117,128],"explicitly.":[118],"enhance":[120],"correlation":[122],"between":[123,154],"spaces,":[129],"introduce":[131],"visual":[133,139,147,209,264],"concepts":[134,148],"represent":[138],"information":[140],"textual":[142],"format.":[143],"In":[144],"manner,":[146],"help":[149],"bridge":[151],"gap":[153],"two":[156,169],"modalities.":[157],"We":[158],"pre-train":[159],"on":[161,168,196,244],"large":[163],"amount":[164],"image\u2013sentence":[166],"pairs":[167],"tasks:":[170],"bidirectional":[171],"modeling":[173],"sequence-to-sequence":[175],"modeling.":[177],"After":[178],"pre-train,":[179],"further":[182],"fine-tuned":[183],"downstream":[186],"Experiments":[188],"show":[189],"sets":[192],"new":[193],"state-of-the-art":[194],"performance":[195],"three":[197],"(over":[199],"four":[200],"datasets),":[201],"including":[202],"generation":[204],"(image":[206],"captioning":[207],"storytelling)":[210],"classification":[212],"(referring":[214],"expressions).":[215],"The":[216],"DiM":[218,260],"ultimodal-Attention)":[224],"module":[225],"easily":[228],"incorporated":[229],"into":[230],"existing":[231],"boost":[236],"their":[237],"performance,":[238],"up":[239],"5%":[242],"increase":[243],"representative":[246],"task.":[247],"Finally,":[248],"conduct":[250],"systematic":[252],"analysis":[253],"demonstrate":[255],"effectiveness":[257],"our":[259],"introduced":[263],"concepts.":[265]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}