{"id":"https://openalex.org/W4394896960","doi":"https://doi.org/10.1109/tcsvt.2024.3390133","title":"GBC: Guided Alignment and Adaptive Boosting CLIP Bridging Vision and Language for Robust Action Recognition","display_name":"GBC: Guided Alignment and Adaptive Boosting CLIP Bridging Vision and Language for Robust Action Recognition","publication_year":2024,"publication_date":"2024-04-17","ids":{"openalex":"https://openalex.org/W4394896960","doi":"https://doi.org/10.1109/tcsvt.2024.3390133"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3390133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3390133","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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":"https://openalex.org/A5052641051","display_name":"Zhaoqilin Yang","orcid":"https://orcid.org/0000-0002-3676-4761"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaoqilin Yang","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China","Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China","Institute of Information Science, Beijing Jiaotong University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054342134","display_name":"Gaoyun An","orcid":"https://orcid.org/0000-0002-2843-843X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoyun An","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China","Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China","Institute of Information Science, Beijing Jiaotong University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052963418","display_name":"Zhenxing Zheng","orcid":"https://orcid.org/0000-0002-6749-4952"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenxing Zheng","raw_affiliation_strings":["School of Communications and Information Engineering, Xi’an University of Posts and Telecommunications, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Communications and Information Engineering, Xi’an University of Posts and Telecommunications, Xi’an, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054546022","display_name":"Shan Cao","orcid":"https://orcid.org/0000-0003-0829-9230"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Cao","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China","Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China","Institute of Information Science, Beijing Jiaotong University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112109951","display_name":"Qiuqi Ruan","orcid":"https://orcid.org/0000-0001-8107-7365"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuqi Ruan","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China","Institute of Information Science, Beijing Jiaotong University, Beijing, Beijing, China","Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052641051"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":2.722,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91178266,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"34","issue":"9","first_page":"8172","last_page":"8187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9980999827384949,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9980999827384949,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.983299970626831,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9545000195503235,"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/bridging","display_name":"Bridging (networking)","score":0.8030291795730591},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7463831305503845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7259820699691772},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.7039854526519775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.628422737121582},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5593215227127075},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3538450002670288},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3523401916027069},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.06573677062988281}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8030291795730591},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7463831305503845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259820699691772},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.7039854526519775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.628422737121582},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5593215227127075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3538450002670288},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3523401916027069},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.06573677062988281},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3390133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3390133","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1859168551","display_name":null,"funder_award_id":"2021YFE0110500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5521863753","display_name":null,"funder_award_id":"62072028","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6863005883","display_name":null,"funder_award_id":"62302391","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W345900524","https://openalex.org/W652269744","https://openalex.org/W1974210421","https://openalex.org/W1988790447","https://openalex.org/W2039454245","https://openalex.org/W2044913453","https://openalex.org/W2126579184","https://openalex.org/W2171061940","https://openalex.org/W2295598076","https://openalex.org/W2552383788","https://openalex.org/W2613763509","https://openalex.org/W2619947201","https://openalex.org/W2724511873","https://openalex.org/W2740825418","https://openalex.org/W2770804203","https://openalex.org/W2796633859","https://openalex.org/W2883429621","https://openalex.org/W2887051120","https://openalex.org/W2894629025","https://openalex.org/W2904378456","https://openalex.org/W2962914678","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2981385151","https://openalex.org/W2990152177","https://openalex.org/W2996994994","https://openalex.org/W3004732066","https://openalex.org/W3012362498","https://openalex.org/W3035047011","https://openalex.org/W3035254087","https://openalex.org/W3035303837","https://openalex.org/W3081704724","https://openalex.org/W3095669214","https://openalex.org/W3138516171","https://openalex.org/W3159557112","https://openalex.org/W3174568846","https://openalex.org/W3175528717","https://openalex.org/W3182022070","https://openalex.org/W3183137097","https://openalex.org/W3186835416","https://openalex.org/W3187343781","https://openalex.org/W3200114289","https://openalex.org/W3205497712","https://openalex.org/W4210915468","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4214727094","https://openalex.org/W4214746887","https://openalex.org/W4220863439","https://openalex.org/W4221166843","https://openalex.org/W4280533444","https://openalex.org/W4281752744","https://openalex.org/W4285600359","https://openalex.org/W4296079457","https://openalex.org/W4297697565","https://openalex.org/W4312263092","https://openalex.org/W4312276384","https://openalex.org/W4312516520","https://openalex.org/W4312560592","https://openalex.org/W4312614039","https://openalex.org/W4312658081","https://openalex.org/W4312769131","https://openalex.org/W4313159427","https://openalex.org/W4313482657","https://openalex.org/W4313886816","https://openalex.org/W4317552047","https://openalex.org/W4322731056","https://openalex.org/W4366351162","https://openalex.org/W4368232702","https://openalex.org/W4382467086","https://openalex.org/W4386065852","https://openalex.org/W4386072441","https://openalex.org/W4386076398","https://openalex.org/W4390872179","https://openalex.org/W4390872466","https://openalex.org/W4393112844","https://openalex.org/W4394597798","https://openalex.org/W6697609866","https://openalex.org/W6754337694","https://openalex.org/W6757817989","https://openalex.org/W6770390784","https://openalex.org/W6782388713","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6801567822","https://openalex.org/W6803794721","https://openalex.org/W6840599879","https://openalex.org/W6850042764","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4388870064","https://openalex.org/W4231274751","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951"],"abstract_inverted_index":{"The":[0,202],"Contrastive":[1],"Language-Image":[2],"Pre-training":[3],"(CLIP)":[4],"model":[5,41,60,118,161,191,206,229],"achieves":[6,230],"strong":[7],"generalization":[8],"by":[9],"using":[10],"a":[11,64,76,100,177,182],"large":[12],"number":[13],"of":[14,137,204],"text-image":[15],"pairs":[16],"for":[17],"contrastive":[18],"learning.":[19],"However,":[20],"when":[21],"it":[22],"is":[23,84,113,142,162,186,207],"transferred":[24],"to":[25,33,38,42,48,57,67,110,119,127,130,164,188,200,234],"action":[26,211],"recognition,":[27],"the":[28,40,59,117,134,139,160,166,172,190],"following":[29],"two":[30],"questions":[31],"remain":[32],"be":[34,128],"solved:":[35],"1)":[36],"How":[37,56],"guide":[39],"focus":[43,192],"more":[44,193],"on":[45,194,209,237],"human-body-related":[46],"regions":[47],"better":[49,120],"align":[50,121],"actions":[51,123],"and":[52,54,79,91,96,144,155,175,219,225],"text,":[53],"2)":[55],"make":[58,189],"strengthen":[61],"itself":[62],"in":[63,99,171],"targeted":[65],"manner":[66,174],"deal":[68],"with":[69,124],"difficult-to-classify":[70],"categories.":[71],"To":[72],"solve":[73],"these":[74],"problems,":[75],"Guided":[77],"alignment":[78],"adaptive":[80],"Boosting":[81,173],"CLIP":[82,140],"(GBC)":[83],"proposed,":[85],"which":[86,115],"employs":[87],"visual":[88,106],"prior":[89,107],"knowledge":[90,108],"benefits":[92],"from":[93,168],"both":[94,222],"feature":[95,147],"decision":[97,149],"aggregation":[98,150],"boosting":[101],"manner.":[102],"During":[103],"early":[104],"training,":[105,138],"related":[109],"human":[111,122],"body":[112],"adopted,":[114],"enables":[116],"category":[125],"text":[126],"robust":[129],"distribution":[131],"shift.":[132],"At":[133],"later":[135],"stage":[136],"encoder":[141],"frozen,":[143],"multiple":[145],"downstream":[146],"&":[148],"modules":[151],"are":[152,198],"sequentially":[153],"generated":[154],"trained.":[156],"In":[157],"such":[158],"way,":[159],"able":[163],"boost":[165],"performance":[167],"different":[169],"perspectives":[170],"at":[176],"linearly":[178],"increasing":[179],"cost.":[180],"Moreover,":[181],"class-adaptive":[183],"re-weighting":[184],"strategy":[185],"proposed":[187],"optimizing":[195],"categories":[196],"that":[197],"difficult":[199],"classify.":[201],"effectiveness":[203],"our":[205],"validated":[208],"six":[210],"recognition":[212],"datasets":[213],"(Kinetics-600,":[214],"Kinetics-400,":[215],"Jester,":[216],"HMDB-51,":[217],"UCF-101,":[218],"Mini-Kinetics-200),":[220],"including":[221],"fully":[223],"supervised":[224],"zero-shot":[226],"experiments.":[227],"Our":[228],"superior":[231],"results":[232],"compared":[233],"state-of-the-art":[235],"methods":[236],"all":[238],"datasets.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}