{"id":"https://openalex.org/W4225314877","doi":"https://doi.org/10.1109/icassp43922.2022.9747849","title":"Transtl: Spatial-Temporal Localization Transformer for Multi-Label Video Classification","display_name":"Transtl: Spatial-Temporal Localization Transformer for Multi-Label Video Classification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225314877","doi":"https://doi.org/10.1109/icassp43922.2022.9747849"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747849","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"https://openalex.org/A5002247003","display_name":"Hongjun Wu","orcid":"https://orcid.org/0000-0003-1436-5732"},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongjun Wu","raw_affiliation_strings":["Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China","Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China","institution_ids":["https://openalex.org/I114234892"]},{"raw_affiliation_string":"Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China","institution_ids":["https://openalex.org/I114234892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020650589","display_name":"Mengzhu Li","orcid":"https://orcid.org/0000-0002-7404-9152"},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengzhu Li","raw_affiliation_strings":["Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China","Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China","institution_ids":["https://openalex.org/I114234892"]},{"raw_affiliation_string":"Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China","institution_ids":["https://openalex.org/I114234892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007288633","display_name":"Yongcheng Liu","orcid":"https://orcid.org/0000-0001-9289-7131"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongcheng Liu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China","Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040452780","display_name":"Hongzhe Liu","orcid":"https://orcid.org/0000-0003-2314-5272"},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhe Liu","raw_affiliation_strings":["Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China","Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China","institution_ids":["https://openalex.org/I114234892"]},{"raw_affiliation_string":"Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China","institution_ids":["https://openalex.org/I114234892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052315039","display_name":"Cheng Xu","orcid":"https://orcid.org/0000-0003-4913-5371"},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Xu","raw_affiliation_strings":["Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China","Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China","institution_ids":["https://openalex.org/I114234892"]},{"raw_affiliation_string":"Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China","institution_ids":["https://openalex.org/I114234892"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100429597","display_name":"Xuewei Li","orcid":"https://orcid.org/0000-0002-5330-7298"},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuewei Li","raw_affiliation_strings":["Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China","Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China","institution_ids":["https://openalex.org/I114234892"]},{"raw_affiliation_string":"Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, China","institution_ids":["https://openalex.org/I114234892"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5002247003"],"corresponding_institution_ids":["https://openalex.org/I114234892"],"apc_list":null,"apc_paid":null,"fwci":0.2998,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61963496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1965","last_page":"1969"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9959999918937683,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9854999780654907,"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":0.7577099800109863},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6634939312934875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6243460774421692},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5277750492095947},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5066249966621399},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.4313018321990967},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41163116693496704},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37925490736961365},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08167093992233276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577099800109863},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6634939312934875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6243460774421692},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5277750492095947},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5066249966621399},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.4313018321990967},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41163116693496704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37925490736961365},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08167093992233276},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747849","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322664","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2292288263","https://openalex.org/W2337252826","https://openalex.org/W2583815496","https://openalex.org/W2770804203","https://openalex.org/W2806331055","https://openalex.org/W2932399282","https://openalex.org/W2943833595","https://openalex.org/W2963091558","https://openalex.org/W2963524571","https://openalex.org/W2963722382","https://openalex.org/W2964015378","https://openalex.org/W2990503944","https://openalex.org/W2997136715","https://openalex.org/W3016459781","https://openalex.org/W3090578762","https://openalex.org/W3099518117","https://openalex.org/W3176747907","https://openalex.org/W4214516465","https://openalex.org/W4214614183","https://openalex.org/W4214673031","https://openalex.org/W4312560592","https://openalex.org/W4385245566","https://openalex.org/W6703281212","https://openalex.org/W6726873649","https://openalex.org/W6739901393","https://openalex.org/W6746798562","https://openalex.org/W6762494229","https://openalex.org/W6785160296","https://openalex.org/W6794642395","https://openalex.org/W6797737728"],"related_works":["https://openalex.org/W2787993192","https://openalex.org/W2158269427","https://openalex.org/W4381280689","https://openalex.org/W3033859939","https://openalex.org/W2847365777","https://openalex.org/W2039871688","https://openalex.org/W3128025644","https://openalex.org/W2355048207","https://openalex.org/W2017214274","https://openalex.org/W4281776617"],"abstract_inverted_index":{"Multi-label":[0],"video":[1,12,85],"classification":[2],"(MLVC)":[3],"is":[4,104],"a":[5,45,64,84,100],"long-standing":[6],"and":[7,25,35,108,118,123,143],"challenging":[8,140],"research":[9],"problem":[10],"in":[11,22,73,83],"signal":[13],"analysis.":[14],"Generally,":[15],"there":[16],"exist":[17],"many":[18],"complex":[19],"action":[20,58,113],"labels":[21,114],"real-world":[23],"videos":[24],"these":[26],"actions":[27],"are":[28],"with":[29],"inherent":[30],"dependencies":[31,95],"at":[32,115],"both":[33,116],"spatial":[34,117],"temporal":[36,119],"domains.":[37,120],"Motivated":[38],"by":[39,86],"this":[40],"observation,":[41],"we":[42,61],"propose":[43,63],"TranSTL,":[44],"spatial-temporal":[46,93],"localization":[47],"Transformer":[48],"framework":[49],"for":[50],"MLVC":[51],"task.":[52],"In":[53],"addition":[54],"to":[55,106],"leverage":[56],"global":[57],"label":[59,81,94],"co-occurrence,":[60],"also":[62,90],"novel":[65],"plug-and-play":[66],"Spatial":[67],"Temporal":[68],"Label":[69],"Dependency":[70],"(STLD)":[71],"layer":[72],"TranSTL.":[74],"STLD":[75],"not":[76],"only":[77],"dynamically":[78],"models":[79],"the":[80,111,133,136],"co-occurrence":[82],"self-attention":[87],"mechanism,":[88],"but":[89],"fully":[91],"captures":[92],"using":[96],"cross-attention":[97],"strategy.":[98],"As":[99],"result,":[101],"our":[102],"TranSTL":[103,128],"able":[105],"explicitly":[107],"accurately":[109],"grasp":[110],"diverse":[112],"Extensive":[121],"evaluation":[122],"empirical":[124],"analysis":[125],"show":[126],"that":[127],"achieves":[129],"superior":[130],"performance":[131],"over":[132],"state":[134],"of":[135],"arts":[137],"on":[138],"two":[139],"benchmarks,":[141],"Charades":[142],"Multi-Thumos.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
