{"id":"https://openalex.org/W4368232702","doi":"https://doi.org/10.1109/tcsvt.2023.3272627","title":"Learning Spatio-Temporal Semantics and Cluster Relation for Zero-Shot Action Recognition","display_name":"Learning Spatio-Temporal Semantics and Cluster Relation for Zero-Shot Action Recognition","publication_year":2023,"publication_date":"2023-05-03","ids":{"openalex":"https://openalex.org/W4368232702","doi":"https://doi.org/10.1109/tcsvt.2023.3272627"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3272627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3272627","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/A5065554199","display_name":"Jiajun Gao","orcid":"https://orcid.org/0000-0003-3098-6619"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Gao","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-3098-6619","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023247075","display_name":"Yonghong Hou","orcid":"https://orcid.org/0000-0002-1676-5505"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Hou","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-1676-5505","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031676073","display_name":"Zihui Guo","orcid":"https://orcid.org/0000-0001-8917-1102"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihui Guo","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-8917-1102","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044709394","display_name":"Haochun Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haochun Zheng","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3473,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82825835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"33","issue":"11","first_page":"6519","last_page":"6530"},"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":0.9891999959945679,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9684000015258789,"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":0.6762990951538086},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6319952011108398},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5973494052886963},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5914018154144287},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5511922836303711},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5160641074180603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.513960063457489},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.46885403990745544},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.4335263669490814},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4151049256324768},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3847358226776123},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35571610927581787},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24116551876068115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23499023914337158},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.12673237919807434},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09173524379730225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6762990951538086},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6319952011108398},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5973494052886963},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5914018154144287},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5511922836303711},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5160641074180603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.513960063457489},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.46885403990745544},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.4335263669490814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4151049256324768},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3847358226776123},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35571610927581787},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24116551876068115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23499023914337158},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.12673237919807434},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09173524379730225},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3272627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3272627","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W652269744","https://openalex.org/W841113906","https://openalex.org/W1498368596","https://openalex.org/W1614298861","https://openalex.org/W1805946669","https://openalex.org/W2044913453","https://openalex.org/W2064851185","https://openalex.org/W2070625895","https://openalex.org/W2100771357","https://openalex.org/W2108598243","https://openalex.org/W2126579184","https://openalex.org/W2142900973","https://openalex.org/W2209594346","https://openalex.org/W2250539671","https://openalex.org/W2289084343","https://openalex.org/W2289324734","https://openalex.org/W2334493732","https://openalex.org/W2346746376","https://openalex.org/W2463762378","https://openalex.org/W2473032611","https://openalex.org/W2507611421","https://openalex.org/W2519055561","https://openalex.org/W2520613337","https://openalex.org/W2560129302","https://openalex.org/W2724511873","https://openalex.org/W2891574165","https://openalex.org/W2896457183","https://openalex.org/W2897439619","https://openalex.org/W2897811550","https://openalex.org/W2904378456","https://openalex.org/W2910021422","https://openalex.org/W2928966231","https://openalex.org/W2961193895","https://openalex.org/W2962914678","https://openalex.org/W2963152432","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2965373098","https://openalex.org/W2981965938","https://openalex.org/W2989322838","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3014645216","https://openalex.org/W3016459781","https://openalex.org/W3021385015","https://openalex.org/W3021778166","https://openalex.org/W3035254087","https://openalex.org/W3096804376","https://openalex.org/W3097217077","https://openalex.org/W3142341292","https://openalex.org/W3143107425","https://openalex.org/W3176125528","https://openalex.org/W3185605671","https://openalex.org/W3190693140","https://openalex.org/W3195949276","https://openalex.org/W3217340782","https://openalex.org/W4214746887","https://openalex.org/W4220910168","https://openalex.org/W4225603090","https://openalex.org/W4285216227","https://openalex.org/W4289362009","https://openalex.org/W4309368547","https://openalex.org/W4312254032","https://openalex.org/W4312584871","https://openalex.org/W4319452844","https://openalex.org/W4322746933","https://openalex.org/W4323897056","https://openalex.org/W6600983433","https://openalex.org/W6636510571","https://openalex.org/W6754524658","https://openalex.org/W6755207826","https://openalex.org/W6765307894","https://openalex.org/W6766578407","https://openalex.org/W6776881853","https://openalex.org/W6784702030","https://openalex.org/W6810507967","https://openalex.org/W6838586047","https://openalex.org/W6846465385","https://openalex.org/W6849846199"],"related_works":["https://openalex.org/W2128807628","https://openalex.org/W1555966012","https://openalex.org/W4234264766","https://openalex.org/W2415426693","https://openalex.org/W2750434199","https://openalex.org/W2135356905","https://openalex.org/W2129428289","https://openalex.org/W2347374138","https://openalex.org/W2050635624","https://openalex.org/W2091753323"],"abstract_inverted_index":{"Zero-shot":[0],"Action":[1],"Recognition":[2],"(ZSAR)":[3],"aims":[4],"at":[5],"bridging":[6],"the":[7,28,32,48,52,73,79,98,109,126,129,142,145,153],"video":[8,99],"<inline-formula":[9],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[10],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[11],"<tex-math":[12],"notation=\"LaTeX\">$\\rightarrow":[13],"$":[14],"</tex-math></inline-formula>":[15],"class":[16],"relation":[17],"with":[18],"only":[19],"labeled":[20],"training":[21],"data":[22],"of":[23,34,128,144],"seen":[24],"classes":[25],"while":[26],"generalizing":[27],"model":[29],"to":[30,71,77,96],"alleviate":[31],"heterogeneity":[33],"unseen":[35],"actions.":[36],"Most":[37],"existing":[38],"methods":[39],"have":[40],"comprehensively":[41],"represented":[42],"videos":[43],"and":[44,51,111,118,137,148],"action":[45],"classes,":[46],"however,":[47],"semantic":[49,80],"gap":[50],"hubness":[53,130],"problem":[54],"between":[55],"them":[56],"remain":[57],"crucial":[58],"challenges":[59],"that":[60,107],"are":[61],"under-explored.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,82,102],"propose":[67,103],"an":[68],"effective":[69],"method":[70],"tackle":[72],"above":[74],"issues.":[75],"Specifically,":[76],"narrow":[78],"gap,":[81],"end-to-end":[83],"generate":[84],"a":[85,104,115],"spatio-temporal":[86],"semantics":[87],"for":[88],"each":[89],"video,":[90],"which":[91],"provides":[92],"essential":[93],"textual":[94],"information":[95],"refine":[97],"representation.":[100],"Furthermore,":[101],"compactness-separability":[105],"loss":[106],"optimizes":[108],"intra-":[110],"inter-class":[112],"relations":[113],"in":[114],"unified":[116],"formula":[117],"quantitatively":[119],"constrains":[120],"cluster":[121],"distribution,":[122],"thus":[123],"effectively":[124],"diminishing":[125],"impact":[127],"problem.":[131],"Extensive":[132],"experiments":[133],"on":[134],"UCF101,":[135],"HMDB51,":[136],"Olympic":[138],"Sports":[139],"datasets":[140],"prove":[141],"effectiveness":[143],"proposed":[146],"approach":[147,151],"demonstrate":[149],"our":[150],"outperforms":[152],"state-of-the-art":[154],"methods.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}