{"id":"https://openalex.org/W4317951278","doi":"https://doi.org/10.48550/arxiv.2301.09595","title":"Zorro: the masked multimodal transformer","display_name":"Zorro: the masked multimodal transformer","publication_year":2023,"publication_date":"2023-01-23","ids":{"openalex":"https://openalex.org/W4317951278","doi":"https://doi.org/10.48550/arxiv.2301.09595"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2301.09595","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.09595","pdf_url":"https://arxiv.org/pdf/2301.09595","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.09595","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020406406","display_name":"Adri\u00e0 Recasens","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Recasens, Adri\u00e0","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023093421","display_name":"Jason Lin","orcid":"https://orcid.org/0000-0002-6277-8729"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Jason","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082760977","display_name":"Jo\u0101o Carreira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carreira, Jo\u0101o","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075387480","display_name":"Drew Jaegle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaegle, Drew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101524928","display_name":"Luyu Wang","orcid":"https://orcid.org/0000-0003-2882-3503"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Luyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012826868","display_name":"Jean-Baptiste Alayrac","orcid":"https://orcid.org/0000-0002-3071-4157"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alayrac, Jean-baptiste","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030447052","display_name":"Pauline Luc","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luc, Pauline","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021766835","display_name":"Antoine Miech","orcid":"https://orcid.org/0000-0001-6657-7812"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miech, Antoine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061684299","display_name":"Lucas Smaira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Smaira, Lucas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025502434","display_name":"Ross Hemsley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hemsley, Ross","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zisserman, Andrew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9909999966621399,"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":0.7854471206665039},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7486494183540344},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6879521012306213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4976840317249298},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4929375648498535},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46065354347229004},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4399407207965851},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4134880304336548},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2632095217704773}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7854471206665039},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7486494183540344},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6879521012306213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4976840317249298},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4929375648498535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46065354347229004},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4399407207965851},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4134880304336548},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2632095217704773},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2301.09595","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.09595","pdf_url":"https://arxiv.org/pdf/2301.09595","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2301.09595","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2301.09595","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.09595","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.09595","pdf_url":"https://arxiv.org/pdf/2301.09595","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4317951278.pdf","grobid_xml":"https://content.openalex.org/works/W4317951278.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Attention-based":[0],"models":[1,67,144],"are":[2,32,97,145],"appealing":[3],"for":[4,135],"multimodal":[5,136],"processing":[6],"because":[7],"inputs":[8,93],"from":[9,94],"multiple":[10],"modalities":[11],"can":[12],"be":[13,43,69],"concatenated":[14],"and":[15,54,119,121,139,154],"fed":[16],"to":[17,57,90,112,147],"a":[18,85],"single":[19],"backbone":[20],"network":[21],"-":[22],"thus":[23],"requiring":[24],"very":[25],"little":[26],"fusion":[27],"engineering.":[28],"The":[29],"resulting":[30,143],"representations":[31],"however":[33],"fully":[34],"entangled":[35],"throughout":[36],"the":[37,105,142],"network,":[38],"which":[39],"may":[40],"not":[41],"always":[42],"desirable:":[44],"in":[45,62],"learning,":[46],"contrastive":[47,125],"audio-visual":[48,66],"self-supervised":[49],"learning":[50,60],"requires":[51],"independent":[52],"audio":[53,75,155],"visual":[55],"features":[56],"operate,":[58],"otherwise":[59],"collapses;":[61],"inference,":[63],"evaluation":[64],"of":[65,104],"should":[68],"possible":[70],"on":[71,131,151],"benchmarks":[72,134,156],"having":[73],"just":[74,77],"or":[76,160],"video.":[78],"In":[79],"this":[80,110],"paper,":[81],"we":[82],"introduce":[83],"Zorro,":[84],"technique":[86,111],"that":[87,123],"uses":[88],"masks":[89],"control":[91],"how":[92],"each":[95],"modality":[96],"routed":[98],"inside":[99],"Transformers,":[100],"keeping":[101],"some":[102],"parts":[103],"representation":[106],"modality-pure.":[107],"We":[108],"apply":[109],"three":[113],"popular":[114],"transformer-based":[115],"architectures":[116],"(ViT,":[117],"Swin":[118],"HiP)":[120],"show":[122],"with":[124],"pre-training":[126],"Zorro":[127],"achieves":[128],"state-of-the-art":[129],"results":[130],"most":[132],"relevant":[133],"tasks":[137],"(AudioSet":[138],"VGGSound).":[140],"Furthermore,":[141],"able":[146],"perform":[148],"unimodal":[149],"inference":[150],"both":[152],"video":[153],"such":[157],"as":[158],"Kinetics-400":[159],"ESC-50.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}