{"id":"https://openalex.org/W7130677675","doi":"https://doi.org/10.1007/s12559-026-10560-3","title":"Weakly Supervised Temporal Action Localization Based on Feature Enhancement","display_name":"Weakly Supervised Temporal Action Localization Based on Feature Enhancement","publication_year":2026,"publication_date":"2026-02-21","ids":{"openalex":"https://openalex.org/W7130677675","doi":"https://doi.org/10.1007/s12559-026-10560-3"},"language":"en","primary_location":{"id":"doi:10.1007/s12559-026-10560-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-026-10560-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-026-10560-3.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s12559-026-10560-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126515227","display_name":"Hongying Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I28813325","display_name":"Civil Aviation University of China","ror":"https://ror.org/03je71k37","country_code":"CN","type":"education","lineage":["https://openalex.org/I28813325"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongying Zhang","raw_affiliation_strings":["College of Electronic Information and Automation, Civil Aviation University of China, Jinbei Road No.2898, Dongli District, 300300, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Information and Automation, Civil Aviation University of China, Jinbei Road No.2898, Dongli District, 300300, Tianjin, China","institution_ids":["https://openalex.org/I28813325"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126488524","display_name":"Yi Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I28813325","display_name":"Civil Aviation University of China","ror":"https://ror.org/03je71k37","country_code":"CN","type":"education","lineage":["https://openalex.org/I28813325"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yao","raw_affiliation_strings":["College of Electronic Information and Automation, Civil Aviation University of China, Jinbei Road No.2898, Dongli District, 300300, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Information and Automation, Civil Aviation University of China, Jinbei Road No.2898, Dongli District, 300300, Tianjin, China","institution_ids":["https://openalex.org/I28813325"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5126515227"],"corresponding_institution_ids":["https://openalex.org/I28813325"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21092669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"1","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":0.9837999939918518,"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":0.9837999939918518,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0032999999821186066,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0024999999441206455,"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/feature","display_name":"Feature (linguistics)","score":0.6261000037193298},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6158999800682068},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6029000282287598},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5727999806404114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5665000081062317},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5246999859809875},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4867999851703644},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.4702000021934509},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.40130001306533813}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7861999869346619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7228999733924866},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6261000037193298},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6158999800682068},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6029000282287598},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5665000081062317},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.40130001306533813},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3125},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.3124000132083893},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.30059999227523804},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C19071747","wikidata":"https://www.wikidata.org/wiki/Q1755207","display_name":"Receptive field","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2517000138759613},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s12559-026-10560-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-026-10560-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-026-10560-3.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s12559-026-10560-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-026-10560-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-026-10560-3.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7130677675.pdf","grobid_xml":"https://content.openalex.org/works/W7130677675.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2096621047","https://openalex.org/W2336403884","https://openalex.org/W2597958930","https://openalex.org/W2604113307","https://openalex.org/W2884293275","https://openalex.org/W2895240652","https://openalex.org/W2948229620","https://openalex.org/W2952435096","https://openalex.org/W2962677524","https://openalex.org/W2962709777","https://openalex.org/W2962876901","https://openalex.org/W2963045696","https://openalex.org/W2963524571","https://openalex.org/W2964216549","https://openalex.org/W2983918066","https://openalex.org/W2984478308","https://openalex.org/W2986407524","https://openalex.org/W2988098865","https://openalex.org/W2998702159","https://openalex.org/W3034623254","https://openalex.org/W3035524964","https://openalex.org/W3035585099","https://openalex.org/W3069380482","https://openalex.org/W3097664769","https://openalex.org/W3109715102","https://openalex.org/W3150473382","https://openalex.org/W3173212682","https://openalex.org/W3173874725","https://openalex.org/W3174421047","https://openalex.org/W3174511093","https://openalex.org/W3207927851","https://openalex.org/W4301963599","https://openalex.org/W4312383773","https://openalex.org/W4313024697","https://openalex.org/W4319300229","https://openalex.org/W4372037321","https://openalex.org/W4376956176","https://openalex.org/W4386071694","https://openalex.org/W4402048694","https://openalex.org/W4403780688","https://openalex.org/W4403829888","https://openalex.org/W4404113805","https://openalex.org/W4405566602"],"related_works":[],"abstract_inverted_index":{"Weakly-supervised":[0],"Temporal":[1],"Action":[2],"Localization":[3],"(WTAL)":[4],"aims":[5],"to":[6,30,113,129,150],"accurately":[7],"localize":[8],"and":[9,33,58,88,98,126,168,191],"classify":[10],"action":[11,117,198],"instances":[12],"in":[13,52,133],"untrimmed":[14],"long":[15],"videos":[16],"using":[17],"only":[18],"video-level":[19],"annotations.":[20],"Although":[21],"most":[22],"existing":[23,179],"WTAL":[24,180],"methods":[25],"leverage":[26],"pre-trained":[27],"feature":[28,148],"extractors":[29],"obtain":[31],"RGB":[32],"optical":[34],"flow":[35],"features\u2013thereby":[36],"reducing":[37],"computational":[38],"costs\u2013this":[39],"strategy":[40],"suffers":[41],"from":[42,61],"two":[43,163],"critical":[44],"limitations:":[45],"(1)":[46],"limited":[47],"temporal":[48,110,197],"receptive":[49,111],"fields,":[50],"resulting":[51],"inadequate":[53],"exploitation":[54],"of":[55,124,178,187],"contextual":[56],"information;":[57],"(2)":[59],"interference":[60],"irrelevant":[62],"background":[63,131],"content,":[64],"which":[65,79],"degrades":[66],"overall":[67],"performance.":[68],"To":[69],"address":[70],"these":[71],"issues,":[72],"we":[73],"propose":[74],"a":[75,143],"Feature-Enhanced":[76],"Network":[77],"(FE-Net),":[78],"comprises":[80],"three":[81],"key":[82],"components:":[83],"the":[84,92,99,109,121,134,176,185],"Local":[85],"Feature":[86,102],"Expansion":[87],"Enhancement":[89,95],"Module":[90,96,104],"(LF-EEM),":[91],"Cross-modal":[93],"Fusion":[94,103],"(CEM),":[97],"Cross-temporal":[100],"Gated":[101],"(CGFF).":[105],"Specifically,":[106],"LF-EEM":[107],"expands":[108],"field":[112],"better":[114],"capture":[115],"complete":[116],"instances.":[118],"CEM":[119],"leverages":[120],"complementary":[122],"nature":[123],"auxiliary":[125],"primary":[127,135],"modalities":[128],"suppress":[130],"noise":[132],"modality":[136],"through":[137],"cross-modal":[138],"fusion.":[139],"Furthermore,":[140],"CGFF":[141],"employs":[142],"cross-temporal":[144],"gating":[145],"mechanism":[146],"during":[147],"fusion":[149],"emphasize":[151],"salient":[152],"changes":[153],"across":[154],"time,":[155],"replacing":[156],"simple":[157],"concatenation.":[158],"Extensive":[159],"experiments":[160],"conducted":[161],"on":[162],"large-scale":[164],"benchmark":[165],"datasets,":[166],"THUMOS-14":[167],"ActivityNet":[169],"v1.2,":[170],"demonstrate":[171],"that":[172],"FE-Net":[173],"significantly":[174],"enhances":[175],"performance":[177],"methods.":[181],"These":[182],"results":[183],"validate":[184],"effectiveness":[186],"our":[188],"proposed":[189],"modules":[190],"provide":[192],"new":[193],"insights":[194],"for":[195],"advancing":[196],"localization":[199],"under":[200],"weak":[201],"supervision.":[202]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-02-21T00:00:00"}