{"id":"https://openalex.org/W3090190336","doi":"https://doi.org/10.3233/faia200412","title":"Weak Supervision Helps Emergence of Word-Object Alignment and Improves Vision-Language Tasks","display_name":"Weak Supervision Helps Emergence of Word-Object Alignment and Improves Vision-Language Tasks","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3090190336","doi":"https://doi.org/10.3233/faia200412","mag":"3090190336"},"language":"en","primary_location":{"id":"doi:10.3233/faia200412","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200412","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia200412","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064783559","display_name":"Corentin Kervadec","orcid":"https://orcid.org/0000-0003-1284-1037"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Kervadec Corentin","raw_affiliation_strings":["Orange Labs [Cesson-S\u00e9vign\u00e9] (4 Rue du Clos Courtel, 35510 Cesson-S\u00e9vign\u00e9 - France)","imagine - Extraction de Caract\u00e9ristiques et Identification (France)"],"affiliations":[{"raw_affiliation_string":"Orange Labs [Cesson-S\u00e9vign\u00e9] (4 Rue du Clos Courtel, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"imagine - Extraction de Caract\u00e9ristiques et Identification (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057376907","display_name":"Grigory Antipov","orcid":"https://orcid.org/0000-0002-8673-9329"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antipov Grigory","raw_affiliation_strings":["Orange Labs [Cesson-S\u00e9vign\u00e9] (4 Rue du Clos Courtel, 35510 Cesson-S\u00e9vign\u00e9 - France)"],"affiliations":[{"raw_affiliation_string":"Orange Labs [Cesson-S\u00e9vign\u00e9] (4 Rue du Clos Courtel, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054284441","display_name":"Moez Baccouche","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Baccouche Moez","raw_affiliation_strings":["Orange Labs [Cesson-S\u00e9vign\u00e9] (4 Rue du Clos Courtel, 35510 Cesson-S\u00e9vign\u00e9 - France)"],"affiliations":[{"raw_affiliation_string":"Orange Labs [Cesson-S\u00e9vign\u00e9] (4 Rue du Clos Courtel, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101613966","display_name":"Christian Wolf","orcid":"https://orcid.org/0000-0001-9766-3211"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wolf Christian","raw_affiliation_strings":["imagine - Extraction de Caract\u00e9ristiques et Identification (France)"],"affiliations":[{"raw_affiliation_string":"imagine - Extraction de Caract\u00e9ristiques et Identification (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064783559"],"corresponding_institution_ids":["https://openalex.org/I19370010"],"apc_list":null,"apc_paid":null,"fwci":0.882,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84004024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9966999888420105,"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":0.9817000031471252,"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":0.7741614580154419},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.7205793261528015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5862478017807007},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5818656086921692},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5327166318893433},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5140677690505981},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4623052179813385},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45748037099838257},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43362683057785034},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.42908474802970886},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11438655853271484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741614580154419},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.7205793261528015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5862478017807007},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5818656086921692},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5327166318893433},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5140677690505981},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4623052179813385},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45748037099838257},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43362683057785034},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.42908474802970886},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11438655853271484},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia200412","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200412","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:1912.03063","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.03063","pdf_url":"https://arxiv.org/pdf/1912.03063","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/faia200412","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200412","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2949603537","https://openalex.org/W3120906802","https://openalex.org/W2972498556","https://openalex.org/W4288334640","https://openalex.org/W4237966389","https://openalex.org/W4239973675","https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3082310784","https://openalex.org/W2964413124"],"abstract_inverted_index":{"The":[0],"large":[1,23],"adoption":[2],"of":[3,18,25,203,210],"the":[4,103,129,131,164,193,208,211,214],"self-attention":[5],"(i.e.":[6],"transformer":[7],"model)":[8],"and\\nBERT-like":[9],"training":[10,77],"principles":[11],"has":[12],"recently":[13],"resulted":[14],"in":[15,97],"a":[16,22,51,196],"number":[17],"high\\nperforming":[19],"models":[20,133,189,215],"on":[21,134,153,171,183,192,213],"panoply":[24],"vision-and-language":[26],"problems":[27],"(such":[28],"as\\nVisual":[29],"Question":[30],"Answering":[31],"(VQA),":[32],"image":[33],"retrieval,":[34],"etc.).":[35],"In":[36,138,174],"this":[37,98,176],"paper":[38],"we":[39,206],"claim\\nthat":[40],"these":[41],"State-Of-The-Art":[42],"(SOTA)":[43],"approaches":[44],"perform":[45],"reasonably":[46],"well":[47],"in\\nstructuring":[48],"information":[49],"inside":[50],"single":[52],"modality":[53],"but,":[54],"despite":[55],"their":[56],"impressive\\nperformances":[57],",":[58,140],"they":[59],"tend":[60],"to":[61,63,73],"struggle":[62],"identify":[64],"fine-grained":[65,166],"inter-modality\\nrelationships.":[66],"Indeed,":[67],"such":[68],"relations":[69],"are":[70],"frequently":[71],"assumed":[72],"be":[74],"implicitly\\nlearned":[75],"during":[76],"from":[78],"application-specific":[79],"losses,":[80],"mostly":[81],"cross-entropy\\nfor":[82],"classification.":[83],"While":[84],"most":[85],"recent":[86],"works":[87],"provide":[88],"inductive":[89],"bias":[90],"for\\ninter-modality":[91],"relationships":[92],"via":[93],"cross":[94],"attention":[95,218],"modules,":[96],"work,":[99],"we\\ndemonstrate":[100],"(1)":[101],"that":[102,118,163],"latter":[104],"assumption":[105],"does":[106,111],"not":[107,112],"hold,":[108],"i.e.":[109],"modality\\nalignment":[110],"necessarily":[113],"emerge":[114],"automatically,":[115],"and":[116,126,150,157,195],"(2)":[117],"adding":[119],"weak\\nsupervision":[120],"for":[121],"alignment":[122,144],"between":[123],"visual":[124],"objects":[125],"words":[127],"improves":[128,169],"quality\\nof":[130],"learned":[132],"tasks":[135,155],"requiring":[136],"reasoning.":[137],"particular":[139],"we\\nintegrate":[141],"an":[142],"object-word":[143],"loss":[145],"into":[146],"SOTA":[147,198],"vision-language":[148],"reasoning\\nmodels":[149],"evaluate":[151],"it":[152],"two":[154],"VQA":[156],"Language-driven":[158],"Comparison":[159,202],"of\\nImages.":[160],"We":[161],"show":[162],"proposed":[165],"inter-modality":[167],"supervision\\nsignificantly":[168],"performance":[170],"both":[172],"tasks.":[173],"particular,":[175],"new\\nlearning":[177],"signal":[178],"allows":[179],"obtaining":[180],"SOTA-level":[181],"performances":[182],"GQA":[184],"dataset":[185,200],"(VQA\\ntask)":[186],"with":[187],"pre-trained":[188],"without":[190],"finetuning":[191],"task,":[194],"new":[197],"on\\nNLVR2":[199],"(Language-driven":[201],"Images).":[204],"Finally,":[205],"also\\nillustrate":[207],"impact":[209],"contribution":[212],"reasoning":[216],"by\\nvisualizing":[217],"distributions.\\n":[219]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}