{"id":"https://openalex.org/W4313190371","doi":"https://doi.org/10.1007/978-3-031-19781-9_24","title":"Learning Audio-Video Modalities from\u00a0Image Captions","display_name":"Learning Audio-Video Modalities from\u00a0Image Captions","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4313190371","doi":"https://doi.org/10.1007/978-3-031-19781-9_24"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-19781-9_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-19781-9_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5036002448","display_name":"Arsha Nagrani","orcid":"https://orcid.org/0000-0003-2190-9013"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arsha Nagrani","raw_affiliation_strings":["Google Research, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051808590","display_name":"Paul Hongsuck Seo","orcid":"https://orcid.org/0000-0002-6747-1101"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Hongsuck Seo","raw_affiliation_strings":["Google Research, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020249437","display_name":"Bryan Seybold","orcid":"https://orcid.org/0000-0001-6081-8347"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Seybold","raw_affiliation_strings":["Google Research, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086681820","display_name":"Anja Hauth","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anja Hauth","raw_affiliation_strings":["Google Research, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069780013","display_name":"Santiago Man\u00e9n","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Santiago Manen","raw_affiliation_strings":["Google Research, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100722234","display_name":"Chen Sun","orcid":"https://orcid.org/0000-0001-8772-9627"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Sun","raw_affiliation_strings":["Google Research, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":["Google Research, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5036002448"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":7.2076,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.97471215,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"407","last_page":"426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9983000159263611,"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/closed-captioning","display_name":"Closed captioning","score":0.9668030738830566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8980379104614258},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.7436769604682922},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6482549905776978},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47917190194129944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4774509072303772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42111027240753174},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4159941077232361},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.28735655546188354}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9668030738830566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8980379104614258},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.7436769604682922},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6482549905776978},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47917190194129944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4774509072303772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42111027240753174},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4159941077232361},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28735655546188354},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-19781-9_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-19781-9_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W753847829","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2010486494","https://openalex.org/W2033740597","https://openalex.org/W2033875152","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2154016477","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2425121537","https://openalex.org/W2463955103","https://openalex.org/W2593116425","https://openalex.org/W2886300652","https://openalex.org/W2886641317","https://openalex.org/W2904106524","https://openalex.org/W2905145027","https://openalex.org/W2914699769","https://openalex.org/W2940092410","https://openalex.org/W2952132648","https://openalex.org/W2952307697","https://openalex.org/W2963017553","https://openalex.org/W2963389687","https://openalex.org/W2963541336","https://openalex.org/W2963916161","https://openalex.org/W2972281329","https://openalex.org/W2980037812","https://openalex.org/W2981537897","https://openalex.org/W2984008963","https://openalex.org/W2984862483","https://openalex.org/W2988753485","https://openalex.org/W3015371781","https://openalex.org/W3015591594","https://openalex.org/W3034556939","https://openalex.org/W3034658206","https://openalex.org/W3035365026","https://openalex.org/W3035635319","https://openalex.org/W3043840704","https://openalex.org/W3092470998","https://openalex.org/W3094502228","https://openalex.org/W3103081334","https://openalex.org/W3105232955","https://openalex.org/W3107806026","https://openalex.org/W3135367836","https://openalex.org/W3167366812","https://openalex.org/W3168640669","https://openalex.org/W3170972077","https://openalex.org/W3174873881","https://openalex.org/W3176398504","https://openalex.org/W3176641147","https://openalex.org/W3196974791","https://openalex.org/W3197828817","https://openalex.org/W3198452188","https://openalex.org/W3203711169","https://openalex.org/W3204588463","https://openalex.org/W4212841753","https://openalex.org/W4285606530","https://openalex.org/W4312384316","https://openalex.org/W6600018615","https://openalex.org/W6601102799","https://openalex.org/W6602046083","https://openalex.org/W6604094065","https://openalex.org/W6604895162","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}