{"id":"https://openalex.org/W3112385539","doi":"https://doi.org/10.1109/cvpr46437.2021.01660","title":"Look Before you Speak: Visually Contextualized Utterances","display_name":"Look Before you Speak: Visually Contextualized Utterances","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3112385539","doi":"https://doi.org/10.1109/cvpr46437.2021.01660","mag":"3112385539"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr46437.2021.01660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.01660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.05710","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Paul Hongsuck Seo","raw_affiliation_strings":["Google Research","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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":false,"raw_author_name":"Arsha Nagrani","raw_affiliation_strings":["Google Research","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","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","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051808590"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.5811,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.668229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"16872","last_page":"16882"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9984999895095825,"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":0.9950000047683716,"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/utterance","display_name":"Utterance","score":0.8894693851470947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8129196763038635},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6604692935943604},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6012247800827026},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5829988718032837},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.526068389415741},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49130120873451233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45567190647125244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4223147928714752},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34428131580352783}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8894693851470947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8129196763038635},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6604692935943604},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6012247800827026},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5829988718032837},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.526068389415741},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49130120873451233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45567190647125244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4223147928714752},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34428131580352783},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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":4,"locations":[{"id":"doi:10.1109/cvpr46437.2021.01660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.01660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2012.05710","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.05710","pdf_url":"https://arxiv.org/pdf/2012.05710","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":"text"},{"id":"mag:3112385539","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2012.05710","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2012.05710","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2012.05710","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2012.05710","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.05710","pdf_url":"https://arxiv.org/pdf/2012.05710","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":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3112385539.pdf"},"referenced_works_count":124,"referenced_works":["https://openalex.org/W10050918","https://openalex.org/W1514535095","https://openalex.org/W1933349210","https://openalex.org/W2005256988","https://openalex.org/W2092651676","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2115090890","https://openalex.org/W2123301721","https://openalex.org/W2143512763","https://openalex.org/W2159573465","https://openalex.org/W2251058040","https://openalex.org/W2311783643","https://openalex.org/W2379107607","https://openalex.org/W2560730294","https://openalex.org/W2603266952","https://openalex.org/W2606982687","https://openalex.org/W2613718673","https://openalex.org/W2734443755","https://openalex.org/W2745461083","https://openalex.org/W2750998636","https://openalex.org/W2765716052","https://openalex.org/W2768661419","https://openalex.org/W2795151422","https://openalex.org/W2796207103","https://openalex.org/W2799263800","https://openalex.org/W2806600904","https://openalex.org/W2810643877","https://openalex.org/W2810840719","https://openalex.org/W2821503932","https://openalex.org/W2883429621","https://openalex.org/W2886641317","https://openalex.org/W2890598214","https://openalex.org/W2891732163","https://openalex.org/W2891969742","https://openalex.org/W2892245540","https://openalex.org/W2911400095","https://openalex.org/W2913636123","https://openalex.org/W2916754336","https://openalex.org/W2949332538","https://openalex.org/W2949600515","https://openalex.org/W2951577137","https://openalex.org/W2954199749","https://openalex.org/W2957775769","https://openalex.org/W2962883855","https://openalex.org/W2962935746","https://openalex.org/W2962949233","https://openalex.org/W2963037989","https://openalex.org/W2963042258","https://openalex.org/W2963223499","https://openalex.org/W2963341956","https://openalex.org/W2963383024","https://openalex.org/W2963403868","https://openalex.org/W2963788376","https://openalex.org/W2964004697","https://openalex.org/W2964094654","https://openalex.org/W2964138017","https://openalex.org/W2964213933","https://openalex.org/W2964220823","https://openalex.org/W2964322347","https://openalex.org/W2964352131","https://openalex.org/W2968104955","https://openalex.org/W2970013683","https://openalex.org/W2970608575","https://openalex.org/W2971172642","https://openalex.org/W2975357369","https://openalex.org/W2975501350","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W2986292373","https://openalex.org/W2990501368","https://openalex.org/W2997443031","https://openalex.org/W3000477803","https://openalex.org/W3004165599","https://openalex.org/W3008593790","https://openalex.org/W3009380496","https://openalex.org/W3014138533","https://openalex.org/W3016658915","https://openalex.org/W3017272398","https://openalex.org/W3020257313","https://openalex.org/W3021065276","https://openalex.org/W3034556939","https://openalex.org/W3034730770","https://openalex.org/W3035339529","https://openalex.org/W3035635319","https://openalex.org/W3037572520","https://openalex.org/W3043840704","https://openalex.org/W3092470998","https://openalex.org/W3096383329","https://openalex.org/W3105232955","https://openalex.org/W3107806026","https://openalex.org/W4249013746","https://openalex.org/W6600392787","https://openalex.org/W6620707391","https://openalex.org/W6623987585","https://openalex.org/W6630875275","https://openalex.org/W6674330103","https://openalex.org/W6678262379","https://openalex.org/W6681236535","https://openalex.org/W6709574965","https://openalex.org/W6736339482","https://openalex.org/W6739901393","https://openalex.org/W6743696045","https://openalex.org/W6750041603","https://openalex.org/W6752764193","https://openalex.org/W6753443365","https://openalex.org/W6755207826","https://openalex.org/W6758736441","https://openalex.org/W6766582784","https://openalex.org/W6766904570","https://openalex.org/W6767853649","https://openalex.org/W6768438993","https://openalex.org/W6770390817","https://openalex.org/W6773596017","https://openalex.org/W6773692765","https://openalex.org/W6774123690","https://openalex.org/W6774609993","https://openalex.org/W6775611549","https://openalex.org/W6775943838","https://openalex.org/W6776909130","https://openalex.org/W6777207437","https://openalex.org/W6780924892","https://openalex.org/W6784184991","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3172523222","https://openalex.org/W3200409912","https://openalex.org/W2950402709","https://openalex.org/W2941492599","https://openalex.org/W3136316642","https://openalex.org/W3004165599","https://openalex.org/W2888185730","https://openalex.org/W3137384391","https://openalex.org/W2979951242","https://openalex.org/W3200524371","https://openalex.org/W2995200518","https://openalex.org/W3014487864","https://openalex.org/W2889077639","https://openalex.org/W3099638501","https://openalex.org/W2809767522","https://openalex.org/W3142625243","https://openalex.org/W3120554508","https://openalex.org/W3166410980","https://openalex.org/W3101240688","https://openalex.org/W3206020652"],"abstract_inverted_index":{"While":[0],"most":[1],"conversational":[2,33],"AI":[3],"systems":[4],"focus":[5],"on":[6,12,121,144,150],"textual":[7,123,131],"dialogue":[8,34],"only,":[9],"conditioning":[10],"utterances":[11],"visual":[13,30,70,125],"context":[14,31],"(when":[15],"it\u2019s":[16],"available)":[17],"can":[18],"lead":[19],"to":[20,90],"more":[21],"realistic":[22],"conversations.":[23],"Unfortunately,":[24],"a":[25,44,50,66,88,112,151],"major":[26],"challenge":[27],"for":[28,99,141],"incorporating":[29],"into":[32],"is":[35],"the":[36,47,62,79,97],"lack":[37],"of":[38,49,82,111,153],"large-scale":[39],"labeled":[40],"datasets.":[41],"We":[42],"provide":[43],"solution":[45],"in":[46,65,105],"form":[48],"new":[51],"visually":[52],"conditioned":[53],"Future":[54],"Utterance":[55],"Prediction":[56],"task.":[57],"Our":[58],"task":[59,93,143],"involves":[60],"predicting":[61],"next":[63],"utterance":[64],"video,":[67],"using":[68],"both":[69,122],"frames":[71],"and":[72,118,124,162],"transcribed":[73],"speech":[74],"as":[75,158],"context.":[76],"By":[77],"exploiting":[78],"large":[80],"number":[81,152],"instructional":[83],"videos":[84,146],"online,":[85],"we":[86,135],"train":[87],"model":[89,109,139],"solve":[91],"this":[92,142],"at":[94],"scale,":[95],"without":[96],"need":[98],"manual":[100],"annotations.":[101],"Leveraging":[102],"recent":[103],"advances":[104],"multimodal":[106,115],"learning,":[107],"our":[108,138],"consists":[110],"novel":[113],"co-attentional":[114],"video":[116],"transformer,":[117],"when":[119],"trained":[120,140],"context,":[126],"outperforms":[127],"baselines":[128],"that":[129,137],"use":[130],"inputs":[132],"alone.":[133],"Further,":[134],"demonstrate":[136],"unlabelled":[145],"achieves":[147],"state-of-the-art":[148],"performance":[149],"downstream":[154],"VideoQA":[155],"benchmarks":[156],"such":[157],"MSRVTT-QA,":[159],"MSVD-QA,":[160],"ActivityNet-QA":[161],"How2QA.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}