{"id":"https://openalex.org/W3190693140","doi":"https://doi.org/10.1109/tcsvt.2021.3100842","title":"Dense Semantics-Assisted Networks for Video Action Recognition","display_name":"Dense Semantics-Assisted Networks for Video Action Recognition","publication_year":2021,"publication_date":"2021-07-28","ids":{"openalex":"https://openalex.org/W3190693140","doi":"https://doi.org/10.1109/tcsvt.2021.3100842","mag":"3190693140"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2021.3100842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3100842","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/A5085348492","display_name":"Haonan Luo","orcid":"https://orcid.org/0000-0002-9121-2687"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN","SG"],"is_corresponding":true,"raw_author_name":"Haonan Luo","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029912845","display_name":"Guosheng Lin","orcid":"https://orcid.org/0000-0002-0329-7458"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Guosheng Lin","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027545344","display_name":"Yazhou Yao","orcid":"https://orcid.org/0000-0002-0337-9410"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yazhou Yao","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735663","display_name":"Zhenmin Tang","orcid":"https://orcid.org/0000-0001-6708-2205"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenmin Tang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023130798","display_name":"Qingyao Wu","orcid":"https://orcid.org/0000-0002-6771-3932"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyao Wu","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024965898","display_name":"Xian\u2010Sheng Hua","orcid":"https://orcid.org/0000-0002-8232-5049"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiansheng Hua","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5085348492"],"corresponding_institution_ids":["https://openalex.org/I172675005","https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":2.3304,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.90360317,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"32","issue":"5","first_page":"3073","last_page":"3084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9962000250816345,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9923999905586243,"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/computer-science","display_name":"Computer science","score":0.8814655542373657},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7356985807418823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.646722137928009},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5989865064620972},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5894500613212585},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5393204092979431},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.47316962480545044},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4538704752922058},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.4118771553039551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37149661779403687},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33278268575668335},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.18482741713523865},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18163275718688965},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.10222306847572327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8814655542373657},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7356985807418823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.646722137928009},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5989865064620972},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5894500613212585},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5393204092979431},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.47316962480545044},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4538704752922058},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.4118771553039551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37149661779403687},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33278268575668335},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.18482741713523865},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18163275718688965},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.10222306847572327},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2021.3100842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3100842","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/G1285748160","display_name":null,"funder_award_id":"30920021135","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3220463999","display_name":null,"funder_award_id":"AISG-RP-2018-003","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G7000730516","display_name":null,"funder_award_id":"61976116","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8057997982","display_name":null,"funder_award_id":"61876208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W639708223","https://openalex.org/W1489737693","https://openalex.org/W1522734439","https://openalex.org/W1580389772","https://openalex.org/W1836465849","https://openalex.org/W1871385855","https://openalex.org/W1900913856","https://openalex.org/W1903029394","https://openalex.org/W1910657905","https://openalex.org/W1923404803","https://openalex.org/W1923697677","https://openalex.org/W1944615693","https://openalex.org/W1950136256","https://openalex.org/W1983364832","https://openalex.org/W2024868105","https://openalex.org/W2067116588","https://openalex.org/W2095242101","https://openalex.org/W2105101328","https://openalex.org/W2108333036","https://openalex.org/W2108598243","https://openalex.org/W2125215748","https://openalex.org/W2126579184","https://openalex.org/W2142694332","https://openalex.org/W2194775991","https://openalex.org/W2235034809","https://openalex.org/W2336589871","https://openalex.org/W2342662179","https://openalex.org/W2412782625","https://openalex.org/W2471138382","https://openalex.org/W2472293097","https://openalex.org/W2507009361","https://openalex.org/W2518013266","https://openalex.org/W2552900565","https://openalex.org/W2556951257","https://openalex.org/W2560023338","https://openalex.org/W2560474170","https://openalex.org/W2563705555","https://openalex.org/W2566588379","https://openalex.org/W2586564970","https://openalex.org/W2613635555","https://openalex.org/W2619947201","https://openalex.org/W2630837129","https://openalex.org/W2736596806","https://openalex.org/W2751445731","https://openalex.org/W2788945907","https://openalex.org/W2791303549","https://openalex.org/W2795210153","https://openalex.org/W2797382244","https://openalex.org/W2806331055","https://openalex.org/W2891355224","https://openalex.org/W2910281775","https://openalex.org/W2943070176","https://openalex.org/W2962744348","https://openalex.org/W2962899219","https://openalex.org/W2963091558","https://openalex.org/W2963119563","https://openalex.org/W2963150697","https://openalex.org/W2963216700","https://openalex.org/W2963253279","https://openalex.org/W2963445119","https://openalex.org/W2963447094","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2963840672","https://openalex.org/W2964094092","https://openalex.org/W2964123261","https://openalex.org/W2964309882","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2995933538","https://openalex.org/W3015352266","https://openalex.org/W3105214483","https://openalex.org/W6600983433","https://openalex.org/W6638667902","https://openalex.org/W6639780620","https://openalex.org/W6640295612","https://openalex.org/W6682864246","https://openalex.org/W6696085341","https://openalex.org/W6729814214","https://openalex.org/W6739696289","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4287776258","https://openalex.org/W4200528772","https://openalex.org/W2603501458","https://openalex.org/W3027997911","https://openalex.org/W2767651786","https://openalex.org/W3021430260","https://openalex.org/W2912288872","https://openalex.org/W2941155331","https://openalex.org/W1526789715","https://openalex.org/W2905846897"],"abstract_inverted_index":{"Most":[0],"existing":[1,37,230],"action":[2,48,84,155,254],"recognition":[3],"approaches":[4],"directly":[5],"leverage":[6,133],"the":[7,23,29,66,81,96,102,115,118,123,147,152,187,192,198,203],"video-level":[8],"features":[9],"to":[10,79,113,173,245],"recognize":[11],"human":[12,127],"actions":[13],"from":[14,41,95],"videos.":[15],"Although":[16],"these":[17],"methods":[18,38,231,248],"have":[19],"made":[20],"remarkable":[21],"progress,":[22],"accuracy":[24],"is":[25,49,77,164,243],"still":[26],"unsatisfied.":[27],"When":[28],"test":[30],"video":[31,57,67,98,120,180],"involves":[32],"complex":[33],"backgrounds":[34],"and":[35,106,122,150,219,232],"activities,":[36],"usually":[39],"suffer":[40],"a":[42,51,56,61,159,182],"significant":[43],"drop":[44],"in":[45,186,197],"accuracy.":[46],"Human":[47],"inherently":[50],"high-level":[52,124],"concept.":[53],"Merely":[54],"applying":[55],"classification":[58],"model":[59],"without":[60],"detailed":[62],"semantic":[63,87,93,135,141,177],"understanding":[64,88],"of":[65,89,104,126,154,179,194,205],"content,":[68],"e.g.,":[69],"objects,":[70],"scene":[71],"context,":[72],"object":[73,75],"motions,":[74],"interactions,":[76],"inadequate":[78],"tackle":[80],"challenges":[82],"for":[83,146,253],"recognition.":[85,156,255],"Fine-level":[86],"videos":[90],"generates":[91],"elementary":[92],"concepts":[94],"raw":[97,119],"data,":[99],"such":[100],"as":[101,166],"semantics":[103],"objects":[105],"background":[107],"regions.":[108],"It":[109,237],"can":[110],"be":[111],"employed":[112],"bridge":[114],"gap":[116],"between":[117],"data":[121],"concept":[125],"actions.":[128],"In":[129],"this":[130],"work,":[131],"we":[132,208],"dense":[134,176],"segmentation":[136],"masks,":[137],"which":[138,163],"encode":[139],"rich":[140],"details,":[142],"provide":[143],"extra":[144,251],"information":[145,178,252],"network":[148],"training,":[149],"improve":[151],"performance":[153],"We":[157],"propose":[158],"novel":[160],"deep":[161],"architecture":[162],"named":[165],"Dense":[167],"Semantics-Assisted":[168],"Convolutional":[169],"Neural":[170],"Networks":[171],"(DSA-CNNs)":[172],"effectively":[174],"utilize":[175,250],"by":[181,191],"bottom-up":[183],"attention":[184],"way":[185,193],"spatial":[188],"stream,":[189],"while":[190],"branch":[195],"fusion":[196],"temporal":[199],"stream.":[200],"To":[201],"verify":[202],"effectiveness":[204],"our":[206,226,241],"approach,":[207],"conduct":[209],"extensive":[210],"experiments":[211],"on":[212],"publicly":[213],"available":[214],"datasets":[215],"\u2013":[216],"UCF101,":[217],"HMDB51,":[218],"Kinetics.":[220],"The":[221],"experimental":[222],"results":[223],"demonstrate":[224],"that":[225,240,249],"approach":[227,242],"substantially":[228],"improves":[229],"achieves":[233],"very":[234],"competitive":[235],"performance.":[236],"also":[238],"shows":[239],"superior":[244],"other":[246],"related":[247]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}