{"id":"https://openalex.org/W4224329855","doi":"https://doi.org/10.1109/tcsvt.2022.3169842","title":"Attention in Attention: Modeling Context Correlation for Efficient Video Classification","display_name":"Attention in Attention: Modeling Context Correlation for Efficient Video Classification","publication_year":2022,"publication_date":"2022-04-22","ids":{"openalex":"https://openalex.org/W4224329855","doi":"https://doi.org/10.1109/tcsvt.2022.3169842"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3169842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3169842","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/A5043525989","display_name":"Yanbin Hao","orcid":"https://orcid.org/0000-0002-0695-1566"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbin Hao","raw_affiliation_strings":["CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science and School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-0695-1566","affiliations":[{"raw_affiliation_string":"CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science and School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400159","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0002-4881-9344"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science and School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-4881-9344","affiliations":[{"raw_affiliation_string":"CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science and School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018517771","display_name":"P.P. Cao","orcid":"https://orcid.org/0000-0001-8469-7447"},"institutions":[{"id":"https://openalex.org/I4210155232","display_name":"Fiberhome Technology Group (China)","ror":"https://ror.org/04yv20134","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155232"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pei Cao","raw_affiliation_strings":["Wuhan Research Institute of Posts and Telecommunications, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0001-8469-7447","affiliations":[{"raw_affiliation_string":"Wuhan Research Institute of Posts and Telecommunications, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I4210155232"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101420810","display_name":"Xinjian Gao","orcid":"https://orcid.org/0000-0001-7638-9022"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinjian Gao","raw_affiliation_strings":["School of Computer Science and Information Engineering and the School of Artificial Intelligence, Hefei University of Technology, Hefei Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-7638-9022","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering and the School of Artificial Intelligence, Hefei University of Technology, Hefei Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025292786","display_name":"Tong Xu","orcid":"https://orcid.org/0000-0003-4246-5386"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xu","raw_affiliation_strings":["School of Data Science and the School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-4246-5386","affiliations":[{"raw_affiliation_string":"School of Data Science and the School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053355549","display_name":"Jinmeng Wu","orcid":"https://orcid.org/0000-0002-0264-8025"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinmeng Wu","raw_affiliation_strings":["Hubei Key Laboratory of Optical Information and Pattern Recognition, Wuhan Institute of Technology, Wuhan, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Optical Information and Pattern Recognition, Wuhan Institute of Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038668215","display_name":"Xiangnan He","orcid":"https://orcid.org/0000-0001-8472-7992"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangnan He","raw_affiliation_strings":["CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science and School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-8472-7992","affiliations":[{"raw_affiliation_string":"CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science and School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4828,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.96990905,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"32","issue":"10","first_page":"7120","last_page":"7132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.8198782801628113},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7146357893943787},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6559496521949768},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.617923378944397},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5871122479438782},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5428497791290283},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5198336243629456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5054693222045898},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4541158676147461},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4417590796947479},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.4317914843559265},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.42507773637771606},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41276800632476807},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32289767265319824},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2723631262779236},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1198011040687561},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09079653024673462}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198782801628113},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7146357893943787},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6559496521949768},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.617923378944397},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5871122479438782},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5428497791290283},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5198336243629456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5054693222045898},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4541158676147461},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4417590796947479},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.4317914843559265},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.42507773637771606},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41276800632476807},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32289767265319824},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2723631262779236},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1198011040687561},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09079653024673462},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3169842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3169842","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/G1111288224","display_name":null,"funder_award_id":"2020YFB1406703","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2469121228","display_name":null,"funder_award_id":"62101524","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3379573397","display_name":null,"funder_award_id":"U21B2026","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1947481528","https://openalex.org/W2016053056","https://openalex.org/W2194775991","https://openalex.org/W2507009361","https://openalex.org/W2625366777","https://openalex.org/W2752782242","https://openalex.org/W2770804203","https://openalex.org/W2806331055","https://openalex.org/W2883429621","https://openalex.org/W2884585870","https://openalex.org/W2884797191","https://openalex.org/W2889418103","https://openalex.org/W2894463902","https://openalex.org/W2895243423","https://openalex.org/W2895299763","https://openalex.org/W2898732869","https://openalex.org/W2902709482","https://openalex.org/W2914868535","https://openalex.org/W2950160919","https://openalex.org/W2951143549","https://openalex.org/W2951702519","https://openalex.org/W2962858109","https://openalex.org/W2962902341","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963465031","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2964213043","https://openalex.org/W2981385151","https://openalex.org/W2984192355","https://openalex.org/W2988277473","https://openalex.org/W2988630963","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2996901793","https://openalex.org/W2996937600","https://openalex.org/W2997004687","https://openalex.org/W3006408808","https://openalex.org/W3034572008","https://openalex.org/W3034600407","https://openalex.org/W3034768625","https://openalex.org/W3035303837","https://openalex.org/W3035413240","https://openalex.org/W3035619757","https://openalex.org/W3047680120","https://openalex.org/W3093270130","https://openalex.org/W3101367838","https://openalex.org/W3119205652","https://openalex.org/W3160173571","https://openalex.org/W3161696079","https://openalex.org/W3202823782","https://openalex.org/W4205432963","https://openalex.org/W6678174250","https://openalex.org/W6749916090","https://openalex.org/W6753924131","https://openalex.org/W6756688856","https://openalex.org/W6756911974","https://openalex.org/W6773433808","https://openalex.org/W6777648310","https://openalex.org/W6780915843","https://openalex.org/W6781350655"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"Attention":[0],"mechanisms":[1],"have":[2],"significantly":[3],"boosted":[4],"the":[5,14,20,43,62,70,86,90,94,115,141,153,158,164,169,177],"performance":[6,66],"of":[7,16,33,64,88,135,148,157,217],"video":[8,24,116,201,211],"classification":[9,212],"neural":[10],"networks":[11],"thanks":[12],"to":[13,41,55,100,109,151],"utilization":[15,58],"perspective":[17],"contexts.":[18],"However,":[19],"current":[21],"research":[22],"on":[23,28,176,208],"attention":[25,96,143,160,173],"generally":[26],"focuses":[27],"adopting":[29],"a":[30,123],"specific":[31,124],"aspect":[32],"contexts":[34,118],"(e.g.,":[35],"channel,":[36],"spatial/temporal,":[37],"or":[38],"global":[39,127],"context)":[40],"refine":[42],"features":[44],"and":[45,59,103,129,204],"neglects":[46],"their":[47],"underlying":[48],"correlation":[49],"when":[50],"computing":[51],"attentions.":[52],"This":[53],"leads":[54],"incomplete":[56],"context":[57,92,149],"hence":[60],"bears":[61],"weakness":[63],"limited":[65],"improvement.":[67],"To":[68,190],"tackle":[69],"problem,":[71],"this":[72],"paper":[73],"proposes":[74],"an":[75,136],"efficient":[76],"attention-in-attention":[77],"(AIA)":[78],"method":[79],"for":[80],"element-wise":[81],"feature":[82,117],"refinement,":[83],"which":[84,180],"investigates":[85],"feasibility":[87],"inserting":[89],"channel":[91],"into":[93,198],"spatio-temporal":[95],"learning":[97],"module,":[98],"referred":[99,108],"as":[101,110,119],"CinST,":[102],"also":[104],"its":[105],"reverse":[106],"variant,":[107],"STinC.":[111],"Specifically,":[112],"we":[113,194],"instantiate":[114],"dynamics":[120],"aggregated":[121],"along":[122],"axis":[125],"with":[126],"average":[128],"max":[130],"pooling":[131],"operations.":[132],"The":[133,214],"workflow":[134],"AIA":[137,219],"module":[138],"is":[139,220],"that":[140,161],"first":[142],"block":[144],"uses":[145],"one":[146],"kind":[147],"information":[150],"guide":[152],"gating":[154],"weights":[155],"calculation":[156],"second":[159],"targets":[162],"at":[163,222],"other":[165],"context.":[166],"Moreover,":[167],"all":[168],"computational":[170,185],"operations":[171],"in":[172,182],"units":[174],"act":[175],"pooled":[178],"dimension,":[179],"results":[181],"quite":[183],"few":[184],"cost":[186],"increase":[187],"(<":[188],"0.02%).":[189],"verify":[191],"our":[192,218],"method,":[193],"densely":[195],"integrate":[196],"it":[197],"two":[199],"classical":[200],"network":[202],"backbones":[203],"conduct":[205],"extensive":[206],"experiments":[207],"several":[209],"standard":[210],"benchmarks.":[213],"source":[215],"code":[216],"available":[221],"<uri":[223],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[224],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/haoyanbin918/Attention-in-Attention</uri>":[225],".":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}