{"id":"https://openalex.org/W4390190295","doi":"https://doi.org/10.1109/iccvw60793.2023.00296","title":"Alignment and Generation Adapter for Efficient Video-text Understanding","display_name":"Alignment and Generation Adapter for Efficient Video-text Understanding","publication_year":2023,"publication_date":"2023-10-02","ids":{"openalex":"https://openalex.org/W4390190295","doi":"https://doi.org/10.1109/iccvw60793.2023.00296"},"language":"en","primary_location":{"id":"doi:10.1109/iccvw60793.2023.00296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw60793.2023.00296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"article","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":null,"display_name":"Han Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Fang","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047206667","display_name":"Zhifei Yang","orcid":"https://orcid.org/0000-0003-0054-8896"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifei Yang","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&AI Technology Company","Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043915216","display_name":"Yuhan Wei","orcid":"https://orcid.org/0000-0002-1663-8100"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]},{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yuhan Wei","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&AI Technology Company","Rice University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]},{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047237045","display_name":"Xianghao Zang","orcid":"https://orcid.org/0000-0001-8421-7167"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianghao Zang","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093130774","display_name":"Chao Ban","orcid":"https://orcid.org/0009-0000-8114-103X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Ban","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019172074","display_name":"Zerun Feng","orcid":"https://orcid.org/0000-0003-3987-0591"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zerun Feng","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101320954","display_name":"Zhongjiang He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjiang He","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373505","display_name":"Yongxiang Li","orcid":"https://orcid.org/0000-0002-3888-9170"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxiang Li","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063142903","display_name":"Hao Sun","orcid":"https://orcid.org/0009-0007-7917-1628"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["China Telecom Corporation Ltd. Data&AI Technology Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Corporation Ltd. Data&AI Technology Company","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7445,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73826669,"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":"2783","last_page":"2789"},"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":0.9944000244140625,"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":0.9837999939918518,"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/adapter","display_name":"Adapter (computing)","score":0.8856519460678101},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.881599485874176},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7881449460983276},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6496207118034363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4064915180206299},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3429969549179077},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.12704163789749146}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.8856519460678101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.881599485874176},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7881449460983276},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6496207118034363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4064915180206299},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3429969549179077},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.12704163789749146},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw60793.2023.00296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw60793.2023.00296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2150824314","https://openalex.org/W2425121537","https://openalex.org/W2774267535","https://openalex.org/W2885775891","https://openalex.org/W2963916161","https://openalex.org/W2964018924","https://openalex.org/W2965458216","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3127602238","https://openalex.org/W3168867926","https://openalex.org/W3174873881","https://openalex.org/W3180463990","https://openalex.org/W3204588463","https://openalex.org/W3205021045","https://openalex.org/W3217340782","https://openalex.org/W4221146248","https://openalex.org/W4285606530","https://openalex.org/W4295990387","https://openalex.org/W4304014690","https://openalex.org/W4307106676","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312463400","https://openalex.org/W4312535570","https://openalex.org/W4312655527","https://openalex.org/W4322718191","https://openalex.org/W4361229539","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4377164404","https://openalex.org/W4377865169","https://openalex.org/W4378510493","https://openalex.org/W4382464395","https://openalex.org/W4385800687","https://openalex.org/W4386057717","https://openalex.org/W4386066385","https://openalex.org/W4386076424","https://openalex.org/W4386076674","https://openalex.org/W4386083024","https://openalex.org/W4390871765","https://openalex.org/W4394659899","https://openalex.org/W4402671548","https://openalex.org/W6747225742","https://openalex.org/W6766582784","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6803567076","https://openalex.org/W6810042059","https://openalex.org/W6843263998","https://openalex.org/W6848748099","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6851948999","https://openalex.org/W6851950068","https://openalex.org/W6852999659","https://openalex.org/W6853314951","https://openalex.org/W6853515732","https://openalex.org/W6864544085"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2993670781","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Pre-trained":[0],"models":[1,48],"have":[2],"demonstrated":[3],"considerable":[4],"performance,":[5],"especially":[6],"in":[7],"enhancing":[8],"cross-modal":[9,100],"understanding":[10],"between":[11,44],"videos":[12],"and":[13,22,46,99,114,122],"text.":[14],"However,":[15],"fine-tuning":[16],"them":[17],"at":[18],"scale":[19],"becomes":[20],"costly":[21],"poses":[23],"challenges":[24],"for":[25,49,70,89],"adapting":[26],"to":[27,64,83,102],"various":[28],"downstream":[29],"tasks.":[30],"To":[31],"tackle":[32],"these":[33],"challenges,":[34],"we":[35,75,92],"propose":[36,58],"the":[37,66,77,85],"Alignment-generation":[38],"Adapter":[39],"(AGAdapter),":[40],"establishing":[41],"semantic":[42],"coherence":[43],"alignment":[45,60],"generation":[47,78],"efficient":[50],"video-text":[51,112],"adaptation":[52],"across":[53],"multiple":[54],"tasks":[55],"simultaneously.":[56],"We":[57],"an":[59],"adapter":[61,79],"with":[62,80],"knowledge-sharing":[63],"adapt":[65],"frozen":[67],"CLIP":[68],"model":[69,88],"fine-grained":[71],"video-language":[72],"interaction.":[73],"Additionally,":[74],"introduce":[76,93],"prompt":[81],"tuning":[82],"leverage":[84],"large":[86],"language":[87],"captioning.":[90],"Furthermore,":[91],"instruction":[94],"joint":[95],"tuning,":[96],"combining":[97],"textual":[98],"instructions,":[101],"capture":[103],"detailed":[104],"descriptions.":[105],"Our":[106],"AGAdapter":[107],"achieves":[108],"state-of-the-art":[109],"performance":[110],"on":[111],"retrieval":[113],"video":[115],"captioning":[116],"tasks,":[117],"including":[118],"two":[119],"benchmarks,":[120],"MSR-VTT":[121],"ActivityNet.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}