乐胖代购免代理版

{"id":"https://openalex.org/W4386523246","doi":"https://doi.org/10.1109/tmm.2023.3312856","title":"Audio-Visual Contrastive and Consistency Learning for Semi-Supervised Action Recognition","display_name":"Audio-Visual Contrastive and Consistency Learning for Semi-Supervised Action Recognition","publication_year":2023,"publication_date":"2023-09-07","ids":{"openalex":"https://openalex.org/W4386523246","doi":"https://doi.org/10.1109/tmm.2023.3312856"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3312856","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5071579962","display_name":"Maregu Assefa","orcid":"https://orcid.org/0000-0003-2815-7993"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maregu Assefa","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101460603","display_name":"Wei Jiang","orcid":"https://orcid.org/0000-0001-6181-3900"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Jiang","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082893987","display_name":"Jinyu Zhan","orcid":"https://orcid.org/0000-0002-0214-7124"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyu Zhan","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108997229","display_name":"Kumie Gedamu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kumie Gedamu","raw_affiliation_strings":["Sichuan Artificial Intelligence Research Institute, Sichuan and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Sichuan Artificial Intelligence Research Institute, Sichuan and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068313046","display_name":"Getinet Yilma","orcid":"https://orcid.org/0000-0001-5577-3201"},"institutions":[{"id":"https://openalex.org/I865572129","display_name":"Adama Science and Technology University","ror":"https://ror.org/02ccba128","country_code":"ET","type":"education","lineage":["https://openalex.org/I865572129"]}],"countries":["ET"],"is_corresponding":false,"raw_author_name":"Getinet Yilma","raw_affiliation_strings":["Department of Computer Science and Engineering, Adama Science and Technology University, Adama, Ethiopia"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Adama Science and Technology University, Adama, Ethiopia","institution_ids":["https://openalex.org/I865572129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109636713","display_name":"Melese Ayalew","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Melese Ayalew","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020543944","display_name":"Deepak Adhikari","orcid":"https://orcid.org/0000-0002-3768-0666"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deepak Adhikari","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.822,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.999956,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":84,"max":88},"biblio":{"volume":"26","issue":null,"first_page":"3491","last_page":"3504"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9992,"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":0.9992,"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":0.9943,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9868,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/leverage","display_name":"Leverage (statistics)","score":0.5685674},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization","score":0.51493937},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature Learning","score":0.49657446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6899129},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5685674},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.51493937},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.49657446},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45220682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44934404},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.44534156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41390255}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3312856","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"62072076"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"62372087"}],"datasets":[],"versions":[],"referenced_works_count":46,"referenced_works":["https://openalex.org/W2126579184","https://openalex.org/W2342662179","https://openalex.org/W2526050071","https://openalex.org/W2619697695","https://openalex.org/W2798991696","https://openalex.org/W2883725317","https://openalex.org/W2936774411","https://openalex.org/W2961193895","https://openalex.org/W2962934715","https://openalex.org/W2963524571","https://openalex.org/W2964159205","https://openalex.org/W2981952041","https://openalex.org/W3034381931","https://openalex.org/W3035524453","https://openalex.org/W3035682985","https://openalex.org/W3091002423","https://openalex.org/W3109620645","https://openalex.org/W3118508703","https://openalex.org/W3145385912","https://openalex.org/W3147788509","https://openalex.org/W3157819479","https://openalex.org/W3164678500","https://openalex.org/W3171007011","https://openalex.org/W3175300676","https://openalex.org/W3176780013","https://openalex.org/W3181598125","https://openalex.org/W3191973200","https://openalex.org/W3209927348","https://openalex.org/W343636949","https://openalex.org/W4206012009","https://openalex.org/W4212880679","https://openalex.org/W4214612132","https://openalex.org/W4221152513","https://openalex.org/W4221162144","https://openalex.org/W4281752744","https://openalex.org/W4287890624","https://openalex.org/W4297697565","https://openalex.org/W4312336798","https://openalex.org/W4312658081","https://openalex.org/W4312661813","https://openalex.org/W4312946625","https://openalex.org/W4313162490","https://openalex.org/W4364353722","https://openalex.org/W4365800727","https://openalex.org/W4366307892","https://openalex.org/W4372259853"],"related_works":["https://openalex.org/W4381280689","https://openalex.org/W4304185162","https://openalex.org/W3033859939","https://openalex.org/W3006282800","https://openalex.org/W2847365777","https://openalex.org/W2787993192","https://openalex.org/W2462100143","https://openalex.org/W2158269427","https://openalex.org/W2061685118","https://openalex.org/W1603736412"],"abstract_inverted_index":{"Semi-supervised":[0],"video":[1,10,153],"learning":[2,30,130,135],"is":[3,171,208],"an":[4,195],"increasingly":[5],"popular":[6],"approach":[7],"for":[8,37,41,102],"improving":[9],"understanding":[11],"tasks":[12],"by":[13,173],"utilizing":[14],"large-scale":[15],"unlabeled":[16],"videos":[17],"along":[18],"with":[19,188],"a":[20],"few":[21],"labels.":[22],"Recent":[23],"studies":[24],"have":[25,201],"shown":[26],"that":[27,203],"multimodal":[28],"contrastive":[29,126,129,134],"and":[31,57,98,132,152,191,214],"consistency":[32,192],"regularization":[33,193],"are":[34,49],"effective":[35,209],"techniques":[36],"generating":[38],"high-quality":[39,82],"pseudo-labels":[40,83,109],"semi-supervised":[42,103,197,218],"action":[43,104,219],"recognition.":[44,105],"However,":[45],"existing":[46,216],"pseudo-labeling":[47],"approaches":[48],"solely":[50],"based":[51],"on":[52,87],"the":[53,65,156,169,181,186,204],"model's":[54],"class":[55],"predictions":[56],"can":[58],"suffer":[59],"from":[60,110,141,177],"confirmation":[61,120,212],"biases":[62,213],"due":[63],"to":[64,80,118,137,160,180],"accumulation":[66],"of":[67,85,165],"false":[68],"predictions.":[69],"To":[70,90],"address":[71],"this":[72,92],"issue,":[73],"we":[74,94],"propose":[75],"exploiting":[76],"audio-visual":[77,111,142,166],"feature":[78,112],"correlations":[79,113],"achieve":[81,91],"instead":[84],"relying":[86],"model":[88,187],"confidence.":[89],"goal,":[93],"introduce":[95],"Audio-visual":[96],"Contrastive":[97],"Consistency":[99],"Learning":[100],"(AvCLR)":[101],"AvCLR":[106,123,206],"generates":[107],"reliable":[108],"using":[114],"deep":[115],"embedded":[116],"clustering":[117],"mitigate":[119],"biases.":[121],"Additionally,":[122],"introduces":[124],"two":[125],"modules:":[127],"intra-modal":[128],"(ImCL)":[131],"cross-modal":[133],"(XmCL)":[136],"discover":[138],"complementary":[139],"information":[140],"alignments.":[143],"The":[144],"ImCL":[145],"module":[146,158],"learns":[147],"informative":[148],"representations":[149],"within":[150],"audio":[151],"independently,":[154],"while":[155],"XmCL":[157,170],"aims":[159],"leverage":[161],"global":[162],"high-level":[163],"features":[164],"information.":[167],"Furthermore,":[168],"constrained":[172],"introducing":[174],"intra-instance":[175],"negatives":[176],"one":[178],"modality":[179],"other.":[182],"We":[183],"jointly":[184],"optimize":[185],"ImCL,":[189],"XmCL,":[190],"in":[194,210],"end-to-end":[196],"manner.":[198],"Experimental":[199],"results":[200],"demonstrated":[202],"proposed":[205],"framework":[207],"reducing":[211],"outperforms":[215],"confidence-based":[217],"recognition":[220],"methods.":[221]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4386523246","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2024-12-21T00:58:14.010791","created_date":"2023-09-08"}