{"id":"https://openalex.org/W3204670646","doi":"https://doi.org/10.1109/iccv48922.2021.01136","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","display_name":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","publication_year":2021,"publication_date":"2021-10-01","ids":{"openalex":"https://openalex.org/W3204670646","doi":"https://doi.org/10.1109/iccv48922.2021.01136","mag":"3204670646"},"language":"en","primary_location":{"id":"doi:10.1109/iccv48922.2021.01136","doi":"https://doi.org/10.1109/iccv48922.2021.01136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv48922.2021.01136","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.09980","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101607140","display_name":"Jianwei Yang","orcid":"https://orcid.org/0000-0002-2167-2880","observed_orcids":["https://orcid.org/0000-0002-2167-2880"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianwei Yang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041302228","display_name":"Yonatan Bisk","orcid":"https://orcid.org/0000-0002-2111-9081","observed_orcids":["https://orcid.org/0000-0002-2111-9081"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonatan Bisk","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047233371","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-6371-505X","observed_orcids":["https://orcid.org/0000-0002-6371-505X"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.3633,"has_fulltext":true,"cited_by_count":122,"citation_normalized_percentile":{"value":0.97856796,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":92,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11542","last_page":"11552"},"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":0.0,"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/T11439","display_name":"Video Analysis and Summarization","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/video-text-alignment","display_name":"video-text alignment","score":0.9490000009536743},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.9570000171661377},{"id":"https://openalex.org/keywords/hard-negative-examples","display_name":"hard negative examples","score":0.9380000233650208},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8109999895095825},{"id":"https://openalex.org/keywords/text-video-retrieval","display_name":"video-text retrieval","score":0.9129999876022339},{"id":"https://openalex.org/keywords/multimodal-representation-learning","display_name":"multimodal representation learning","score":0.8169999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8055524826049805},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8006834983825684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.630798876285553},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5547785758972168},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.541790246963501},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4698468744754791},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.45211657881736755},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4292573928833008},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4277428686618805},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.41188156604766846},{"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv48922.2021.01136","doi":"https://doi.org/10.1109/iccv48922.2021.01136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv48922.2021.01136","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.09980","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.09980","pdf_url":"https://arxiv.org/pdf/2108.09980","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,"listed_in":[],"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.2108.09980","doi":"https://doi.org/10.48550/arxiv.2108.09980","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2108.09980","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.09980","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.09980","pdf_url":"https://arxiv.org/pdf/2108.09980","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3204670646.pdf","grobid_xml":"https://content.openalex.org/works/W3204670646.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1861492603","https://openalex.org/W1927052826","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2120861206","https://openalex.org/W2144211451","https://openalex.org/W2152790380","https://openalex.org/W2185243164","https://openalex.org/W2190067570","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2526286384","https://openalex.org/W2530794863","https://openalex.org/W2565656701","https://openalex.org/W2606982687","https://openalex.org/W2610163825","https://openalex.org/W2619082050","https://openalex.org/W2619947201","https://openalex.org/W2626778328","https://openalex.org/W2760256074","https://openalex.org/W2774267535","https://openalex.org/W2799247651","https://openalex.org/W2883429621","https://openalex.org/W2885775891","https://openalex.org/W2896457183","https://openalex.org/W2897439619","https://openalex.org/W2923016229","https://openalex.org/W2936420065","https://openalex.org/W2948859046","https://openalex.org/W2949650786","https://openalex.org/W2950797609","https://openalex.org/W2952132648","https://openalex.org/W2962934715","https://openalex.org/W2962964995","https://openalex.org/W2963155035","https://openalex.org/W2963341956","https://openalex.org/W2963351113","https://openalex.org/W2963541336","https://openalex.org/W2964094654","https://openalex.org/W2965458216","https://openalex.org/W2970231061","https://openalex.org/W2970608575","https://openalex.org/W2972073579","https://openalex.org/W2975357369","https://openalex.org/W2975813532","https://openalex.org/W2980282514","https://openalex.org/W2981851019","https://openalex.org/W2997591391","https://openalex.org/W3005680577","https://openalex.org/W3006320872","https://openalex.org/W3020712669","https://openalex.org/W3035265375","https://openalex.org/W3035356601","https://openalex.org/W3035524453","https://openalex.org/W3035635319","https://openalex.org/W3043840704","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3105232955","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W3130842207","https://openalex.org/W4409217829","https://openalex.org/W4394862671","https://openalex.org/W4386942867","https://openalex.org/W4294691145","https://openalex.org/W4311252325","https://openalex.org/W7161915110","https://openalex.org/W4305007698","https://openalex.org/W4386065413","https://openalex.org/W3145807616"],"abstract_inverted_index":{"Contrastive":[0],"learning":[1,28,33],"has":[2],"been":[3],"widely":[4],"used":[5],"to":[6,82,103],"train":[7],"transformer-based":[8],"vision-language":[9],"models":[10,132,160],"for":[11,64,112,116,133],"video-text":[12,66],"alignment":[13],"and":[14,77,144,183],"multi-modal":[15,117],"representation":[16],"learning.":[17],"This":[18,57],"paper":[19],"presents":[20],"a":[21,65,97,105,134],"new":[22,172],"algorithm":[23],"called":[24],"Token-Aware":[25],"Cascade":[26],"contrastive":[27,32,43],"(TACo)":[29],"that":[30,63,158],"improves":[31],"using":[34],"two":[35],"novel":[36],"techniques.":[37],"The":[38,155],"first":[39],"is":[40,46,58,101],"the":[41,52,61,68,72,86,90,93,122],"token-aware":[42],"loss":[44,114],"which":[45],"computed":[47],"by":[48,60],"taking":[49],"into":[50],"account":[51],"syntactic":[53],"classes":[54],"of":[55,108,124,136,180],"words.":[56,95],"motivated":[59],"observation":[62],"pair,":[67],"content":[69],"words":[70],"in":[71,89,126],"text,":[73],"such":[74],"as":[75],"nouns":[76],"verbs,":[78],"are":[79],"more":[80],"likely":[81],"be":[83],"aligned":[84],"with":[85],"visual":[87],"contents":[88],"video":[91,146,151],"than":[92],"function":[94],"Second,":[96],"cascade":[98],"sampling":[99],"method":[100],"applied":[102],"generate":[104],"small":[106],"set":[107,135],"hard":[109],"negative":[110],"examples":[111],"efficient":[113],"estimation":[115],"fusion":[118],"layers.":[119],"To":[120],"validate":[121],"effectiveness":[123],"TACo,":[125],"our":[127,159],"experiments":[128],"we":[129],"finetune":[130],"pretrained":[131],"downstream":[137],"tasks":[138],"including":[139],"text-video":[140,177],"retrieval":[141,178],"(YouCook2,":[142],"MSR-VTT":[143,182],"ActivityNet),":[145],"action":[147,152],"step":[148],"localization":[149],"(CrossTask),":[150],"segmentation":[153],"(COIN).":[154],"results":[156],"show":[157],"attain":[161],"consistent":[162],"improvements":[163],"across":[164],"different":[165],"experimental":[166],"settings":[167],"over":[168],"previous":[169],"methods,":[170],"set-ting":[171],"state-of-the-art":[173],"on":[174],"three":[175],"public":[176],"benchmarks":[179],"YouCook2,":[181],"ActivityNet.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":43},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-10-11T00:00:00"}