{"id":"https://openalex.org/W4321021995","doi":"https://doi.org/10.1109/tip.2023.3244411","title":"StochasticFormer: Stochastic Modeling for Weakly Supervised Temporal Action Localization","display_name":"StochasticFormer: Stochastic Modeling for Weakly Supervised Temporal Action Localization","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4321021995","doi":"https://doi.org/10.1109/tip.2023.3244411","pmid":"https://pubmed.ncbi.nlm.nih.gov/37027545"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3244411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3244411","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","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/A5014178940","display_name":"Haichao Shi","orcid":"https://orcid.org/0000-0001-8846-1853"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haichao Shi","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8846-1853","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419434","display_name":"Xiaoyu Zhang","orcid":"https://orcid.org/0000-0003-1630-6058"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Yu Zhang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1630-6058","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330875","display_name":"Changsheng Li","orcid":"https://orcid.org/0000-0001-9789-7632"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Li","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9789-7632","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4654,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.81615084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"1379","last_page":"1389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T11227","display_name":"Diabetic Foot Ulcer Assessment and Management","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9814000129699707,"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":0.7582521438598633},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6629771590232849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5320409536361694},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.46253398060798645},{"id":"https://openalex.org/keywords/snippet","display_name":"Snippet","score":0.4619498550891876},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43183547258377075},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.4223077893257141},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3665306270122528},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.349801242351532},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18489092588424683},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10348397493362427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582521438598633},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6629771590232849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5320409536361694},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.46253398060798645},{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.4619498550891876},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43183547258377075},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.4223077893257141},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3665306270122528},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.349801242351532},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18489092588424683},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10348397493362427},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3244411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3244411","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:37027545","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37027545","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1976224554","display_name":null,"funder_award_id":"U2003111","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2937404559","display_name":null,"funder_award_id":"U2001211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G678045099","display_name":null,"funder_award_id":"62122013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1900913856","https://openalex.org/W1927052826","https://openalex.org/W2095242101","https://openalex.org/W2105101328","https://openalex.org/W2126574503","https://openalex.org/W2342662179","https://openalex.org/W2342776425","https://openalex.org/W2469228190","https://openalex.org/W2507009361","https://openalex.org/W2514167171","https://openalex.org/W2604113307","https://openalex.org/W2766402183","https://openalex.org/W2884002012","https://openalex.org/W2884293275","https://openalex.org/W2895240652","https://openalex.org/W2948229620","https://openalex.org/W2950534130","https://openalex.org/W2962677524","https://openalex.org/W2962709777","https://openalex.org/W2962876901","https://openalex.org/W2962964140","https://openalex.org/W2963247196","https://openalex.org/W2963524571","https://openalex.org/W2963563276","https://openalex.org/W2964214371","https://openalex.org/W2964216549","https://openalex.org/W2983918066","https://openalex.org/W2984478308","https://openalex.org/W2984619425","https://openalex.org/W2986407524","https://openalex.org/W2988098865","https://openalex.org/W2989042503","https://openalex.org/W2990503944","https://openalex.org/W2997063620","https://openalex.org/W2998702159","https://openalex.org/W3002181557","https://openalex.org/W3010504658","https://openalex.org/W3034623254","https://openalex.org/W3035585099","https://openalex.org/W3092499653","https://openalex.org/W3100481960","https://openalex.org/W3109715102","https://openalex.org/W3109986575","https://openalex.org/W3125909557","https://openalex.org/W3164258727","https://openalex.org/W3173212682","https://openalex.org/W3173874725","https://openalex.org/W3174421047","https://openalex.org/W3191337212","https://openalex.org/W6640963894","https://openalex.org/W6752968661","https://openalex.org/W6758711939"],"related_works":["https://openalex.org/W1607713096","https://openalex.org/W3036724449","https://openalex.org/W2798329462","https://openalex.org/W1511521437","https://openalex.org/W3201315194","https://openalex.org/W4318980730","https://openalex.org/W2950904665","https://openalex.org/W2985134635","https://openalex.org/W2023083803","https://openalex.org/W4289376745"],"abstract_inverted_index":{"Weakly":[0],"supervised":[1],"temporal":[2],"action":[3,94,107],"localization":[4,89],"(WS-TAL)":[5],"aims":[6,117],"to":[7,13,59,68,81,118,140,154],"identify":[8],"the":[9,46,65,87,97,102,114,120,124,135,142,152,168,172,178,192,198],"time":[10],"intervals":[11],"corresponding":[12,98],"actions":[14],"of":[15,134,194],"interest":[16],"in":[17],"untrimmed":[18],"videos":[19],"with":[20,96,127,162,197],"video-level":[21,169],"weak":[22],"supervision.":[23],"For":[24],"most":[25],"existing":[26],"WS-TAL":[27],"methods,":[28],"two":[29,184],"commonly":[30],"encountered":[31],"challenges":[32],"are":[33,148],"under-localization":[34],"and":[35,137,144,177,188],"over-localization,":[36],"which":[37,147],"inevitably":[38],"bring":[39],"about":[40],"severe":[41],"performance":[42],"deterioration.":[43],"To":[44],"address":[45],"issues,":[47],"this":[48],"paper":[49],"proposes":[50],"a":[51,77],"transformer-structured":[52],"stochastic":[53,115],"process":[54],"modeling":[55],"framework,":[56],"namely":[57],"StochasticFormer,":[58],"fully":[60],"investigate":[61],"finer-grained":[62],"interactions":[63],"among":[64,123],"intermediate":[66,125],"predictions":[67,126],"achieve":[69],"further":[70],"refined":[71],"localization.":[72],"StochasticFormer":[73,195],"is":[74,160],"built":[75],"on":[76,183],"standard":[78],"attention-based":[79],"pipeline":[80],"derive":[82],"preliminary":[83],"frame/snippet-level":[84],"predictions.":[85,157],"Then,":[86],"pseudo":[88,93,99,103,112],"module":[90],"generates":[91],"variable-length":[92],"instances":[95],"labels.":[100],"Using":[101],"\"action":[104],"instance":[105],"-":[106],"category\"":[108],"pairs":[109],"as":[110],"fine-grained":[111],"supervision,":[113],"modeler":[116],"learn":[119],"underlying":[121],"interaction":[122],"an":[128],"encoder-decoder":[129],"network.":[130],"The":[131,158],"encoder":[132],"consists":[133],"deterministic":[136],"latent":[138],"path":[139],"capture":[141],"local":[143],"global":[145],"information,":[146],"subsequently":[149],"integrated":[150],"by":[151],"decoder":[153],"obtain":[155],"reliable":[156],"framework":[159],"optimized":[161],"three":[163],"carefully":[164],"designed":[165],"losses,":[166],"i.e.":[167],"classification":[170],"loss,":[171,176],"frame-level":[173],"semantic":[174],"coherence":[175],"ELBO":[179],"loss.":[180],"Extensive":[181],"experiments":[182],"benchmarks,":[185],"i.e.,":[186],"THUMOS14":[187],"ActivityNet1.2,":[189],"have":[190],"shown":[191],"efficacy":[193],"compared":[196],"state-of-the-art":[199],"methods.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}