{"id":"https://openalex.org/W4379528708","doi":"https://doi.org/10.1109/tpami.2023.3283067","title":"Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection","display_name":"Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection","publication_year":2023,"publication_date":"2023-06-07","ids":{"openalex":"https://openalex.org/W4379528708","doi":"https://doi.org/10.1109/tpami.2023.3283067","pmid":"https://pubmed.ncbi.nlm.nih.gov/37279118"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3283067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3283067","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100569640","display_name":"Jing Tan","orcid":"https://orcid.org/0009-0005-8016-915X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Tan","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114500342","display_name":"Yuhong Wang","orcid":"https://orcid.org/0009-0009-2510-7940"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhong Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101546753","display_name":"Gangshan Wu","orcid":"https://orcid.org/0000-0003-1391-1762"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangshan Wu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100436505","display_name":"Limin Wang","orcid":"https://orcid.org/0000-0002-3674-7718"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limin Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100569640"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":1.8054,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87233236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"45","issue":"10","first_page":"12506","last_page":"12520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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":0.9994999766349792,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9940000176429749,"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":0.6122351884841919},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5817263722419739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5811992883682251},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5079942345619202},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4070035219192505},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37911975383758545},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3276527523994446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25506341457366943},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10532164573669434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6122351884841919},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5817263722419739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5811992883682251},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5079942345619202},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4070035219192505},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37911975383758545},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3276527523994446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25506341457366943},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10532164573669434},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3283067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3283067","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37279118","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37279118","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1829964333","display_name":null,"funder_award_id":"020214380099","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G528746023","display_name":null,"funder_award_id":"61921006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6791897338","display_name":null,"funder_award_id":"62076119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7937537567","display_name":null,"funder_award_id":"020214380091","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W2063249218","https://openalex.org/W2098498971","https://openalex.org/W2108598243","https://openalex.org/W2109412002","https://openalex.org/W2132579158","https://openalex.org/W2146007701","https://openalex.org/W2156303437","https://openalex.org/W2171186743","https://openalex.org/W2194775991","https://openalex.org/W2477205648","https://openalex.org/W2491875666","https://openalex.org/W2507009361","https://openalex.org/W2578494166","https://openalex.org/W2611596598","https://openalex.org/W2619947201","https://openalex.org/W2896457183","https://openalex.org/W2962677524","https://openalex.org/W2962722947","https://openalex.org/W2962869524","https://openalex.org/W2962876901","https://openalex.org/W2963524571","https://openalex.org/W2963645879","https://openalex.org/W2964311439","https://openalex.org/W2980037812","https://openalex.org/W2983918066","https://openalex.org/W2984287396","https://openalex.org/W2990503944","https://openalex.org/W2997429269","https://openalex.org/W2998582438","https://openalex.org/W3010426832","https://openalex.org/W3034309634","https://openalex.org/W3034364644","https://openalex.org/W3034623254","https://openalex.org/W3034679267","https://openalex.org/W3035303837","https://openalex.org/W3043840704","https://openalex.org/W3048938178","https://openalex.org/W3092462694","https://openalex.org/W3094502228","https://openalex.org/W3095481265","https://openalex.org/W3096609285","https://openalex.org/W3096824106","https://openalex.org/W3099032148","https://openalex.org/W3106041614","https://openalex.org/W3108772932","https://openalex.org/W3111800901","https://openalex.org/W3124314487","https://openalex.org/W3126721948","https://openalex.org/W3128626728","https://openalex.org/W3138516171","https://openalex.org/W3156973125","https://openalex.org/W3168640669","https://openalex.org/W3169064633","https://openalex.org/W3170874841","https://openalex.org/W3173599944","https://openalex.org/W3175528717","https://openalex.org/W3176444885","https://openalex.org/W3184549588","https://openalex.org/W3186413649","https://openalex.org/W3190965961","https://openalex.org/W3199096350","https://openalex.org/W3199858703","https://openalex.org/W3203020760","https://openalex.org/W3213454282","https://openalex.org/W4214607465","https://openalex.org/W4214612132","https://openalex.org/W4221142658","https://openalex.org/W4221166385","https://openalex.org/W4221167396","https://openalex.org/W4283706578","https://openalex.org/W4312509322","https://openalex.org/W4312560592","https://openalex.org/W4385245566","https://openalex.org/W6674697456","https://openalex.org/W6681722295","https://openalex.org/W6682864246","https://openalex.org/W6739901393","https://openalex.org/W6749682228","https://openalex.org/W6755207826","https://openalex.org/W6778485988","https://openalex.org/W6780924892","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6790307280","https://openalex.org/W6790830454","https://openalex.org/W6797737728","https://openalex.org/W6799838802","https://openalex.org/W6810265253","https://openalex.org/W6839672489","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2588198209","https://openalex.org/W1909006023","https://openalex.org/W4205824991","https://openalex.org/W3200723557","https://openalex.org/W4312713546","https://openalex.org/W2362195430","https://openalex.org/W2347494122","https://openalex.org/W2567983276","https://openalex.org/W2802298219","https://openalex.org/W2393996461"],"abstract_inverted_index":{"Generic":[0],"Boundary":[1],"Detection":[2],"(GBD)":[3],"aims":[4],"at":[5],"locating":[6],"the":[7,71,101,122,139,159,168,180,186,192,204,210,233,273,307],"general":[8,62,284],"boundaries":[9,41],"that":[10,306],"divide":[11],"videos":[12],"into":[13,105],"semantically":[14],"coherent":[15],"and":[16,19,154,162,207,259,263,268,297],"taxonomy-free":[17],"units,":[18,119],"could":[20],"serve":[21],"as":[22,97],"an":[23,176],"important":[24],"pre-processing":[25],"step":[26],"for":[27],"long-form":[28],"video":[29,103],"understanding.":[30],"Previous":[31],"works":[32],"often":[33],"separately":[34],"handle":[35,158],"these":[36],"different":[37],"types":[38,147],"of":[39,45,73,93,117,125,132,142,148,170,227,276],"generic":[40,75],"with":[42,64,239],"specific":[43],"designs":[44],"deep":[46],"networks":[47],"from":[48,78],"simple":[49],"CNN":[50],"to":[51,70,81,88,99,113,128,136,166,183,189,291,319],"LSTM.":[52],"Instead,":[53],"in":[54],"this":[55,114],"paper,":[56],"we":[57,144,174,197,287],"present":[58,198],"Temporal":[59,222,278,295],"Perceiver,":[60],"a":[61,67,90,106,129,199,225,283,293],"architecture":[63],"Transformer,":[65],"offering":[66],"unified":[68],"solution":[69],"detection":[72,201,213,312],"arbitrary":[74],"boundaries,":[76],"ranging":[77],"shot-level,":[79],"event-level,":[80],"scene-level":[82],"GBDs.":[83],"Our":[84,230],"core":[85],"design":[86],"is":[87],"introduce":[89],"small":[91],"set":[92],"latent":[94,118,149,171],"feature":[95,150,172],"queries":[96,153,188],"anchors":[98],"compress":[100],"redundant":[102],"input":[104,133],"fixed":[107,115],"dimension":[108],"via":[109],"cross-attention":[110,181],"blocks.":[111],"Thanks":[112],"number":[116],"it":[120],"reduces":[121],"quadratic":[123],"complexity":[124],"attention":[126],"operation":[127],"linear":[130],"form":[131],"frames.":[134],"Specifically,":[135],"explicitly":[137,184],"leverage":[138],"temporal":[140],"structure":[141],"videos,":[143],"construct":[145],"two":[146],"queries:":[151],"boundary":[152,187,194,212],"context":[155],"queries,":[156,173],"which":[157],"semantic":[160],"incoherence":[161],"coherence":[163],"accordingly.":[164],"Moreover,":[165],"guide":[167],"learning":[169],"propose":[175],"alignment":[177],"loss":[178],"on":[179,191,203,224,236],"maps":[182],"encourage":[185],"attend":[190],"top":[193],"candidates.":[195],"Finally,":[196],"sparse":[200],"head":[202],"compressed":[205],"representation,":[206],"directly":[208],"output":[209],"final":[211],"results":[214,235],"without":[215],"any":[216],"post-processing":[217],"module.":[218],"We":[219],"test":[220],"our":[221,277],"Perceiver":[223,309],"variety":[226],"GBD":[228,285],"benchmarks.":[229,303],"method":[231],"obtains":[232],"state-of-the-art":[234],"all":[237,302],"benchmarks":[238],"RGB":[240],"single-stream":[241],"features:":[242],"SoccerNet-v2":[243],"(81.9":[244],"percent":[245,249,253,257,261,266,270],"average-mAP),":[246],"Kinetics-GEBD":[247],"(86.0":[248],"average-f1),":[250,254],"TAPOS":[251],"(73.2":[252],"MovieScenes":[255],"(51.9":[256],"AP":[258,267],"53.1":[260],"M<sub>iou</sub>)":[262],"MovieNet":[264],"(53.3":[265],"53.2":[269],"M<sub>iou</sub>),":[271],"demonstrating":[272],"generalization":[274,316],"ability":[275,317],"Perceiver.":[279],"To":[280],"further":[281],"pursue":[282],"model,":[286],"combine":[288],"various":[289],"tasks":[290],"train":[292],"class-agnostic":[294,308],"perceiver":[296],"evaluate":[298],"its":[299],"performance":[300],"across":[301],"Results":[304],"show":[305],"achieves":[310],"comparable":[311],"accuracy":[313],"but":[314],"better":[315],"compared":[318],"dataset-specific":[320],"counterparts.":[321]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}