{"id":"https://openalex.org/W4391011752","doi":"https://doi.org/10.1142/s0219691323500662","title":"A survey on deep learning-based spatio-temporal action detection","display_name":"A survey on deep learning-based spatio-temporal action detection","publication_year":2024,"publication_date":"2024-01-18","ids":{"openalex":"https://openalex.org/W4391011752","doi":"https://doi.org/10.1142/s0219691323500662"},"language":"en","primary_location":{"id":"doi:10.1142/s0219691323500662","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219691323500662","pdf_url":null,"source":{"id":"https://openalex.org/S56986848","display_name":"International Journal of Wavelets Multiresolution and Information Processing","issn_l":"0219-6913","issn":["0219-6913","1793-690X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Wavelets, Multiresolution and Information Processing","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/A5100396102","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0003-0016-6273"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang 310007, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-0016-6273","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang 310007, P. R. China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101775134","display_name":"Fanwei Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanwei Zeng","raw_affiliation_strings":["Ant Group, Hangzhou, Zhejiang 310007, P. R. China"],"raw_orcid":"https://orcid.org/0009-0005-7872-8610","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, Zhejiang 310007, P. R. China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059857918","display_name":"Yuntao Qian","orcid":"https://orcid.org/0000-0002-7418-5891"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuntao Qian","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang 310007, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-7418-5891","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang 310007, P. R. China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059857918"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":3.095,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92358398,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"22","issue":"04","first_page":null,"last_page":null},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998000264167786,"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":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7762280702590942},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6389868259429932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6229726076126099},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5308792591094971},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4958101212978363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49026039242744446},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.48220574855804443},{"id":"https://openalex.org/keywords/entertainment","display_name":"Entertainment","score":0.4748038351535797},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43529778718948364},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.11702802777290344},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08129256963729858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762280702590942},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6389868259429932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6229726076126099},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5308792591094971},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4958101212978363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49026039242744446},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48220574855804443},{"id":"https://openalex.org/C512170562","wikidata":"https://www.wikidata.org/wiki/Q173799","display_name":"Entertainment","level":2,"score":0.4748038351535797},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43529778718948364},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.11702802777290344},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08129256963729858},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"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/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0219691323500662","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219691323500662","pdf_url":null,"source":{"id":"https://openalex.org/S56986848","display_name":"International Journal of Wavelets Multiresolution and Information Processing","issn_l":"0219-6913","issn":["0219-6913","1793-690X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Wavelets, Multiresolution and Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5507728153","display_name":null,"funder_award_id":"62071421","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8139305836","display_name":null,"funder_award_id":"2023YFE0204200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W1797109199","https://openalex.org/W1927052826","https://openalex.org/W1983364832","https://openalex.org/W2010399676","https://openalex.org/W2016208906","https://openalex.org/W2018068650","https://openalex.org/W2034014085","https://openalex.org/W2095661305","https://openalex.org/W2097342496","https://openalex.org/W2101194540","https://openalex.org/W2102605133","https://openalex.org/W2112796928","https://openalex.org/W2123477621","https://openalex.org/W2126579184","https://openalex.org/W2137981002","https://openalex.org/W2193145675","https://openalex.org/W2292288263","https://openalex.org/W2336403884","https://openalex.org/W2519080876","https://openalex.org/W2549139847","https://openalex.org/W2559655401","https://openalex.org/W2605111198","https://openalex.org/W2611596598","https://openalex.org/W2612076919","https://openalex.org/W2612690371","https://openalex.org/W2618799552","https://openalex.org/W2771583656","https://openalex.org/W2792895102","https://openalex.org/W2883275382","https://openalex.org/W2895738954","https://openalex.org/W2905765182","https://openalex.org/W2947454602","https://openalex.org/W2949343965","https://openalex.org/W2955874753","https://openalex.org/W2962688385","https://openalex.org/W2962790054","https://openalex.org/W2962803561","https://openalex.org/W2963037989","https://openalex.org/W2963091558","https://openalex.org/W2963161140","https://openalex.org/W2963524571","https://openalex.org/W2963529931","https://openalex.org/W2963563276","https://openalex.org/W2963823258","https://openalex.org/W2964072322","https://openalex.org/W2964207322","https://openalex.org/W2981808500","https://openalex.org/W2982277552","https://openalex.org/W2982770724","https://openalex.org/W2987850001","https://openalex.org/W2990503944","https://openalex.org/W2998360624","https://openalex.org/W3009112254","https://openalex.org/W3034572008","https://openalex.org/W3094702047","https://openalex.org/W3096609285","https://openalex.org/W3106250896","https://openalex.org/W3109173645","https://openalex.org/W3131080139","https://openalex.org/W3134906819","https://openalex.org/W3172432880","https://openalex.org/W3173407577","https://openalex.org/W3195209314","https://openalex.org/W3201233545","https://openalex.org/W3203086442","https://openalex.org/W3204116406","https://openalex.org/W3206171662","https://openalex.org/W4212774754","https://openalex.org/W4212975908","https://openalex.org/W4248257644","https://openalex.org/W4304098269","https://openalex.org/W4312509322","https://openalex.org/W4319299890","https://openalex.org/W4322630961","https://openalex.org/W4380986300","https://openalex.org/W4385489236"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Spatio-temporal":[0],"action":[1,104],"detection":[2,99],"(STAD)":[3],"aims":[4],"to":[5,55,83,93,102],"classify":[6],"the":[7,71,88,95,109,120],"actions":[8],"present":[9],"in":[10,16,29,52],"a":[11,23,57,67,79,134],"video":[12],"and":[13,18,45,59,114,119,133],"localize":[14],"them":[15],"space":[17],"time.":[19],"It":[20],"has":[21],"become":[22],"particularly":[24],"active":[25],"area":[26],"of":[27,33,70,122,136,140],"research":[28,138],"computer":[30],"vision":[31],"because":[32],"its":[34],"explosively":[35],"emerging":[36],"real-world":[37],"applications,":[38],"such":[39],"as":[40],"autonomous":[41],"driving,":[42],"visual":[43],"surveillance":[44],"entertainment.":[46],"Many":[47],"efforts":[48],"have":[49],"been":[50],"devoted":[51],"recent":[53],"years":[54],"build":[56],"robust":[58],"effective":[60],"framework":[61],"for":[62,76],"STAD.":[63,77],"This":[64],"paper":[65,130],"provides":[66],"comprehensive":[68],"review":[69],"state-of-the-art":[72,123],"deep":[73],"learning-based":[74],"methods":[75],"First,":[78],"taxonomy":[80],"is":[81,125,131],"developed":[82],"organize":[84],"these":[85],"methods.":[86],"Next,":[87],"linking":[89],"algorithms,":[90],"which":[91],"aim":[92],"associate":[94],"frame-":[96],"or":[97],"clip-level":[98],"results":[100],"together":[101],"form":[103],"tubes,":[105],"are":[106,117,142],"reviewed.":[107],"Then,":[108],"commonly":[110],"used":[111],"benchmark":[112],"datasets":[113],"evaluation":[115],"metrics":[116],"introduced,":[118],"performance":[121],"models":[124],"compared.":[126],"At":[127],"last,":[128],"this":[129],"concluded,":[132],"set":[135],"potential":[137],"directions":[139],"STAD":[141],"discussed.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}