{"id":"https://openalex.org/W4379662646","doi":"https://doi.org/10.1145/3539618.3591721","title":"MAMO: Fine-Grained Vision-Language Representations Learning with Masked Multimodal Modeling","display_name":"MAMO: Fine-Grained Vision-Language Representations Learning with Masked Multimodal Modeling","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4379662646","doi":"https://doi.org/10.1145/3539618.3591721"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-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/A5014609545","display_name":"Zijia Zhao","orcid":"https://orcid.org/0009-0000-7781-932X"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zijia Zhao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040424302","display_name":"Longteng Guo","orcid":"https://orcid.org/0000-0002-4340-4000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Longteng Guo","raw_affiliation_strings":["Bytedance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Bytedance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777772","display_name":"Xingjian He","orcid":"https://orcid.org/0000-0001-5396-6253"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjian He","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068078544","display_name":"Shuai Shao","orcid":"https://orcid.org/0000-0001-8560-4572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Shao","raw_affiliation_strings":["Bytedance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Bytedance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039592275","display_name":"Zehuan Yuan","orcid":"https://orcid.org/0000-0002-0349-9367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehuan Yuan","raw_affiliation_strings":["Bytedance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Bytedance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108392430","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-0903-9131"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5014609545"],"corresponding_institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.8304,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74429468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1528","last_page":"1538"},"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":0.9973999857902527,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9878000020980835,"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":0.8384616374969482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6010599136352539},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5603405237197876},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5407536029815674},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5113384127616882},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47108781337738037},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.461590051651001},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4531926214694977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8384616374969482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6010599136352539},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5603405237197876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5407536029815674},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5113384127616882},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47108781337738037},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.461590051651001},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4531926214694977},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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:10.1145/3539618.3591721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1283858192","display_name":null,"funder_award_id":"U21B2043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1614471940","display_name":null,"funder_award_id":"2020AAA0","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5577970204","display_name":null,"funder_award_id":"2020AAA0106400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7424057548","display_name":null,"funder_award_id":"No. 2020AAA0106400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2560730294","https://openalex.org/W2886641317","https://openalex.org/W2962858109","https://openalex.org/W2963530300","https://openalex.org/W2964345792","https://openalex.org/W2970231061","https://openalex.org/W3035682985","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3159481202","https://openalex.org/W3173151551","https://openalex.org/W3173220247","https://openalex.org/W4312312750","https://openalex.org/W4312460555","https://openalex.org/W4312784228","https://openalex.org/W4312804044","https://openalex.org/W4312877428","https://openalex.org/W4312910992","https://openalex.org/W4313156423","https://openalex.org/W6601630192"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W3204607391","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"Multimodal":[0],"representation":[1],"learning":[2],"has":[3,19],"shown":[4],"promising":[5],"improvements":[6],"on":[7,67,176,190],"various":[8,191],"vision-language":[9,193],"tasks":[10],"(e.g.,":[11,161],"image-text":[12,44,68,196],"retrieval,":[13,197],"visual":[14,123,198,201,205],"question":[15,199],"answering,":[16,200],"etc)":[17],"and":[18,38,70,74,89,94,118,128,156,179,203],"significantly":[20],"advanced":[21],"the":[22,78,97,104,112,150],"development":[23],"of":[24,103,125,130],"multimedia":[25],"information":[26],"systems.":[27],"Most":[28],"existing":[29],"methods":[30],"excel":[31],"at":[32],"building":[33],"global-level":[34],"alignment":[35],"between":[36,153],"vision":[37,93,165],"language":[39],"while":[40],"lacking":[41],"effective":[42],"fine-grained":[43,59,144],"interaction.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50],"a":[51,87,135],"jointly":[52],"masked":[53,79,136],"multimodal":[54,60,101,113,145,171],"modeling":[55,137],"method":[56,63],"to":[57,81],"learn":[58],"representations.":[61],"Our":[62,182],"performs":[64],"joint":[65],"masking":[66],"input":[69],"integrates":[71],"both":[72,177],"implicit":[73,84],"explicit":[75,108],"targets":[76,160],"for":[77,92],"signals":[80],"recover.":[82],"The":[83,107],"target":[85,109],"provides":[86],"unified":[88],"debiased":[90],"objective":[91],"language,":[95],"where":[96],"model":[98,140,184],"predicts":[99],"latent":[100],"representations":[102,114,155,172],"unmasked":[105],"input.":[106],"further":[110],"enriches":[111],"by":[115],"recovering":[116],"high-level":[117,154],"semantically":[119,169],"meaningful":[120],"information:":[121],"momentum":[122],"features":[124],"image":[126,162],"patches":[127],"concepts":[129],"word":[131],"tokens.":[132],"Through":[133],"such":[134],"process,":[138],"our":[139],"not":[141],"only":[142],"learns":[143],"interaction,":[146],"but":[147],"also":[148],"avoids":[149],"semantic":[151],"gap":[152],"low-or":[157],"mid-level":[158],"prediction":[159],"pixels,":[163],"discrete":[164],"tokens),":[166],"thus":[167],"producing":[168],"rich":[170],"that":[173],"perform":[174],"well":[175],"zero-shot":[178],"fine-tuned":[180],"settings.":[181],"pre-trained":[183],"(named":[185],"MAMO)":[186],"achieves":[187],"state-of-the-art":[188],"performance":[189],"downstream":[192],"tasks,":[194],"including":[195],"reasoning,":[202],"weakly-supervised":[204],"grounding.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2023-06-08T00:00:00"}