{"id":"https://openalex.org/W4304080498","doi":"https://doi.org/10.1145/3503161.3548341","title":"MVPTR","display_name":"MVPTR","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080498","doi":"https://doi.org/10.1145/3503161.3548341"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548341","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548341","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5101725946","display_name":"Zejun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zejun Li","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078689432","display_name":"Zhihao Fan","orcid":"https://orcid.org/0000-0002-9910-7937"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Fan","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083156453","display_name":"Huaixiao Tou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaixiao Tou","raw_affiliation_strings":["ByteDance, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373492","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0003-3148-264X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011504177","display_name":"Zhongyu Wei","orcid":"https://orcid.org/0000-0003-3789-8507"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyu Wei","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088834359","display_name":"Xuanjing Huang","orcid":"https://orcid.org/0000-0001-9197-9426"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101725946"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.8989,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82568088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4395","last_page":"4405"},"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":0.9970999956130981,"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":0.9934999942779541,"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":0.8508742451667786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5706678032875061},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.568671703338623},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5604810118675232},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5261511206626892},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5236603617668152},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5137870907783508},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5058740973472595},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4421093165874481},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14272591471672058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8508742451667786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5706678032875061},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.568671703338623},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5604810118675232},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5261511206626892},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5236603617668152},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5137870907783508},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5058740973472595},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4421093165874481},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14272591471672058},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548341","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548341","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W607748843","https://openalex.org/W1773149199","https://openalex.org/W1847618513","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W2185175083","https://openalex.org/W2247513039","https://openalex.org/W2489434015","https://openalex.org/W2506483933","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2963518342","https://openalex.org/W2970231061","https://openalex.org/W2997591391","https://openalex.org/W2998356391","https://openalex.org/W3034837210","https://openalex.org/W3035688398","https://openalex.org/W3081168214","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3096609285","https://openalex.org/W3098232790","https://openalex.org/W3135367836","https://openalex.org/W3166304536","https://openalex.org/W3173220247","https://openalex.org/W3173909648","https://openalex.org/W3174476431","https://openalex.org/W3176824248","https://openalex.org/W3177224328","https://openalex.org/W3207798279","https://openalex.org/W3213106580","https://openalex.org/W4288083516"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2004831463","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W2168054807"],"abstract_inverted_index":{"Previous":[0],"vision-language":[1],"pre-training":[2],"models":[3],"mainly":[4],"construct":[5],"multi-modal":[6,88],"inputs":[7],"with":[8],"tokens":[9,27],"and":[10,28,44,116,129,151,174],"objects":[11],"(pixels)":[12],"followed":[13],"by":[14],"performing":[15],"cross-modality":[16],"interaction":[17],"between":[18],"them.":[19],"We":[20],"argue":[21],"that":[22],"the":[23,48,71,85,98,107,124,142,147,156],"input":[24],"of":[25,74],"only":[26],"object":[29],"features":[30],"limits":[31],"high-level":[32,81],"semantic":[33,61,118],"alignment":[34,62,119],"like":[35],"phrase-to-region":[36],"grounding.":[37],"Meanwhile,":[38],"multi-level":[39,89,104,162],"alignments":[40,163],"are":[41],"inherently":[42],"consistent":[43],"able":[45],"to":[46,58,77,123,145,159],"facilitate":[47],"representation":[49,105,149],"learning":[50,86],"synergistically.":[51],"Therefore,":[52],"in":[53,141,155],"this":[54],"paper,":[55],"we":[56,69,134],"propose":[57],"learn":[59],"Multi-level":[60],"for":[63],"Vision-language":[64],"Pre-TRaining":[65],"(MVPTR).":[66],"In":[67,121],"MVPTR,":[68],"follow":[70],"nested":[72],"structure":[73],"both":[75,114],"modalities":[76,112],"introduce":[78,135],"concepts":[79],"as":[80],"semantics.":[82],"To":[83],"ease":[84],"from":[87],"inputs,":[90],"our":[91],"framework":[92],"is":[93],"split":[94],"into":[95],"two":[96,152],"stages,":[97],"first":[99,143],"stage":[100,144,158],"focuses":[101],"on":[102,171],"intra-modality":[103],"learning,":[106,150],"second":[108,157],"enforces":[109],"interactions":[110],"across":[111,164],"via":[113],"coarse-grained":[115],"fine-grained":[117],"tasks.":[120,176],"addition":[122],"commonly":[125],"used":[126],"image-text":[127],"matching":[128],"masked":[130,137],"language":[131,175],"model":[132,167],"tasks,":[133],"a":[136],"concept":[138,148],"recovering":[139],"task":[140],"enhance":[146],"more":[153],"tasks":[154],"explicitly":[160],"encourage":[161],"modalities.":[165],"Our":[166],"achieves":[168],"state-of-the-art":[169],"results":[170],"several":[172],"vision":[173]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-10-10T00:00:00"}