{"id":"https://openalex.org/W4414144087","doi":"https://doi.org/10.1631/fitee.2500164","title":"Temporal fidelity enhancement for video action recognition","display_name":"Temporal fidelity enhancement for video action recognition","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4414144087","doi":"https://doi.org/10.1631/fitee.2500164"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.2500164","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2500164","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","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/A5111026100","display_name":"Xu Shaowu","orcid":"https://orcid.org/0000-0002-1607-7112"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaowu Xu","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1607-7112","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068966518","display_name":"Xibin Jia","orcid":"https://orcid.org/0000-0001-8799-8042"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xibin Jia","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8799-8042","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010566612","display_name":"Qianmei Sun","orcid":"https://orcid.org/0000-0002-1928-7772"},"institutions":[{"id":"https://openalex.org/I183519381","display_name":"Capital Medical University","ror":"https://ror.org/013xs5b60","country_code":"CN","type":"education","lineage":["https://openalex.org/I183519381"]},{"id":"https://openalex.org/I2800232565","display_name":"Beijing Chao-Yang Hospital, Capital Medical University","ror":"https://ror.org/01eff5662","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2800232565","https://openalex.org/I4210110145","https://openalex.org/I4210135108"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianmei Sun","raw_affiliation_strings":["Beijing Chao-yang Hospital, Capital Medical University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Chao-yang Hospital, Capital Medical University, Beijing, China","institution_ids":["https://openalex.org/I2800232565","https://openalex.org/I183519381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029310930","display_name":"Chang Jing","orcid":"https://orcid.org/0000-0003-2302-8869"},"institutions":[{"id":"https://openalex.org/I183519381","display_name":"Capital Medical University","ror":"https://ror.org/013xs5b60","country_code":"CN","type":"education","lineage":["https://openalex.org/I183519381"]},{"id":"https://openalex.org/I2800232565","display_name":"Beijing Chao-Yang Hospital, Capital Medical University","ror":"https://ror.org/01eff5662","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2800232565","https://openalex.org/I4210110145","https://openalex.org/I4210135108"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chang","raw_affiliation_strings":["Beijing Chao-yang Hospital, Capital Medical University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Chao-yang Hospital, Capital Medical University, Beijing, China","institution_ids":["https://openalex.org/I2800232565","https://openalex.org/I183519381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111026100"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":1.1133,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82089236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"26","issue":"8","first_page":"1293","last_page":"1304"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9965999722480774,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.551800012588501},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5460000038146973},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.49790000915527344},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4625000059604645},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.46209999918937683},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45840001106262207},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4449999928474426},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4325000047683716},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.39010000228881836},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.3813000023365021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293999791145325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5881999731063843},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3765000104904175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.2500164","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2500164","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2056501338","https://openalex.org/W2126579184","https://openalex.org/W2194775991","https://openalex.org/W2337252826","https://openalex.org/W2583815496","https://openalex.org/W2608988379","https://openalex.org/W2770804203","https://openalex.org/W2883429621","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963645879","https://openalex.org/W2963722382","https://openalex.org/W2981385151","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3034572008","https://openalex.org/W3035625410","https://openalex.org/W3096071706","https://openalex.org/W3102937163","https://openalex.org/W3113270693","https://openalex.org/W3119547333","https://openalex.org/W3174568846","https://openalex.org/W3175528717","https://openalex.org/W3176747907","https://openalex.org/W4214614183","https://openalex.org/W4214727094","https://openalex.org/W4312624947","https://openalex.org/W4312757522","https://openalex.org/W4312772544","https://openalex.org/W4319663728","https://openalex.org/W4319878933","https://openalex.org/W4381233075","https://openalex.org/W4382240304","https://openalex.org/W4385627142","https://openalex.org/W4386065852","https://openalex.org/W4386076464","https://openalex.org/W4386076625","https://openalex.org/W4386526950","https://openalex.org/W4388483287","https://openalex.org/W4388854793","https://openalex.org/W4390190427","https://openalex.org/W4393149172","https://openalex.org/W4393160420","https://openalex.org/W4394596448","https://openalex.org/W4394744429","https://openalex.org/W4399126338","https://openalex.org/W4401640270","https://openalex.org/W4404199622","https://openalex.org/W4406611285","https://openalex.org/W4407567895"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W3125091513","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345"],"abstract_inverted_index":{"Temporal":[0],"attention":[1,24,51,116,134],"mechanisms":[2],"are":[3],"essential":[4],"for":[5,103],"video":[6],"action":[7,43,122,159],"recognition,":[8],"enabling":[9],"models":[10,19],"to":[11,53],"focus":[12],"on":[13,78,143],"semantically":[14],"informative":[15],"moments.":[16],"However,":[17],"these":[18],"frequently":[20],"exhibit":[21],"temporal":[22,36,69,87,115,127],"infidelity\u2014misaligned":[23],"weights":[25],"caused":[26],"by":[27,89],"limited":[28],"training":[29],"diversity":[30],"and":[31,129,146],"the":[32,45,79,131,150],"absence":[33],"of":[34,47,133,152],"fine-grained":[35,139],"supervision.":[37,140],"While":[38],"video-level":[39],"labels":[40],"provide":[41],"coarse-grained":[42],"guidance,":[44],"lack":[46],"detailed":[48],"constraints":[49],"allows":[50],"noise":[52],"persist,":[54],"especially":[55],"in":[56,110,158],"complex":[57],"scenarios":[58],"with":[59,113,120,155],"distracting":[60],"spatial":[61],"elements.":[62],"To":[63],"address":[64],"this":[65],"issue,":[66],"we":[67],"propose":[68],"fidelity":[70,132],"enhancement":[71],"(TFE),":[72],"a":[73],"competitive":[74],"learning":[75],"paradigm":[76],"based":[77],"disentangled":[80],"information":[81],"bottleneck":[82],"(DisenIB)":[83],"theory.":[84],"TFE":[85,105],"mitigates":[86],"infidelity":[88],"decoupling":[90],"action-relevant":[91],"semantics":[92],"from":[93],"spurious":[94],"correlations":[95],"through":[96],"adversarial":[97,108],"feature":[98],"disentanglement.":[99],"Using":[100],"pre-trained":[101],"representations":[102],"initialization,":[104],"establishes":[106],"an":[107],"process":[109],"which":[111],"segments":[112],"elevated":[114],"compete":[117],"against":[118],"contexts":[119],"diminished":[121],"relevance.":[123],"This":[124],"mechanism":[125],"ensures":[126],"consistency":[128],"enhances":[130],"patterns":[135],"without":[136],"requiring":[137],"explicit":[138],"Extensive":[141],"studies":[142],"UCF101,":[144],"HMDB-51,":[145],"Charades":[147],"benchmarks":[148],"validate":[149],"effectiveness":[151],"our":[153],"method,":[154],"significant":[156],"improvements":[157],"recognition":[160],"accuracy.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-01T08:36:08.643496","created_date":"2025-10-10T00:00:00"}