{"id":"https://openalex.org/W4414955845","doi":"https://doi.org/10.1109/tmm.2025.3613174","title":"Action-to-Action Diffusion Network for Weakly Supervised Temporal Action Localization","display_name":"Action-to-Action Diffusion Network for Weakly Supervised Temporal Action Localization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414955845","doi":"https://doi.org/10.1109/tmm.2025.3613174"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3613174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3613174","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5072393871","display_name":"Yuanbing Zou","orcid":"https://orcid.org/0000-0001-8950-6929"},"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":"Yuanbing Zou","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044948606","display_name":"Qingjie Zhao","orcid":"https://orcid.org/0000-0002-6955-4170"},"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":"Qingjie Zhao","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6955-4170","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049607460","display_name":"Prodip Kumar Sarker","orcid":"https://orcid.org/0009-0003-4411-3816"},"institutions":[{"id":"https://openalex.org/I168889406","display_name":"Begum Rokeya University","ror":"https://ror.org/00hhr3x36","country_code":"BD","type":"education","lineage":["https://openalex.org/I168889406"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Prodip Kumar Sarker","raw_affiliation_strings":["Department of Computer Science and Engineering, Begum Rokeya University, Rangpur, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Begum Rokeya University, Rangpur, Bangladesh","institution_ids":["https://openalex.org/I168889406"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102528494","display_name":"Le Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le Yang","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China"],"raw_orcid":"https://orcid.org/0000-0001-5922-877X","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043220498","display_name":"Binglu Wang","orcid":"https://orcid.org/0000-0002-9266-4685"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binglu Wang","raw_affiliation_strings":["School of Astronautics, Northwestern Polytechnical University, Xi’an, China","School of Astronautics, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-9266-4685","affiliations":[{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Astronautics, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24221863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"9371","last_page":"9384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9962000250816345,"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":0.9948999881744385,"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/discriminative-model","display_name":"Discriminative model","score":0.800599992275238},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6363999843597412},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5562999844551086},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5210999846458435},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5060999989509583},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4302000105381012},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.414000004529953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008999824523926},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.800599992275238},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.635699987411499},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5210999846458435},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5060999989509583},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4327999949455261},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3613174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3613174","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7883903628","display_name":null,"funder_award_id":"2023TQ0344","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1595717062","https://openalex.org/W1927052826","https://openalex.org/W2105101328","https://openalex.org/W2533503513","https://openalex.org/W2604113307","https://openalex.org/W2884293275","https://openalex.org/W2892664578","https://openalex.org/W2948229620","https://openalex.org/W2952435096","https://openalex.org/W2961553857","https://openalex.org/W2962677524","https://openalex.org/W2962709777","https://openalex.org/W2963045696","https://openalex.org/W2963524571","https://openalex.org/W2964216549","https://openalex.org/W2974686944","https://openalex.org/W2976669726","https://openalex.org/W2981998043","https://openalex.org/W2998702159","https://openalex.org/W3034623254","https://openalex.org/W3097664769","https://openalex.org/W3109715102","https://openalex.org/W3112040205","https://openalex.org/W3118479201","https://openalex.org/W3120494681","https://openalex.org/W3124795329","https://openalex.org/W3172837290","https://openalex.org/W3173212682","https://openalex.org/W3173698268","https://openalex.org/W3173874725","https://openalex.org/W3174421047","https://openalex.org/W3174511093","https://openalex.org/W3175580044","https://openalex.org/W3207927851","https://openalex.org/W4225505766","https://openalex.org/W4226500165","https://openalex.org/W4285030992","https://openalex.org/W4285146284","https://openalex.org/W4301963599","https://openalex.org/W4304084063","https://openalex.org/W4309368547","https://openalex.org/W4312264054","https://openalex.org/W4312317576","https://openalex.org/W4312421085","https://openalex.org/W4313555695","https://openalex.org/W4313644168","https://openalex.org/W4319300229","https://openalex.org/W4362514023","https://openalex.org/W4382203549","https://openalex.org/W4386066210","https://openalex.org/W4386071957","https://openalex.org/W4386076071","https://openalex.org/W4386076495","https://openalex.org/W4386076520","https://openalex.org/W4386159997","https://openalex.org/W4387969575","https://openalex.org/W4388430502","https://openalex.org/W4390872435","https://openalex.org/W4390872970","https://openalex.org/W4390872976","https://openalex.org/W4390873021","https://openalex.org/W4390873541","https://openalex.org/W4390970312","https://openalex.org/W4402727505","https://openalex.org/W4402753985","https://openalex.org/W4402916549"],"related_works":[],"abstract_inverted_index":{"Weakly":[0],"supervised":[1],"temporal":[2],"action":[3,9,58,71,106,149],"localization":[4,27],"(WTAL)":[5],"aims":[6],"to":[7,44,96,127,145,169,180,187],"identify":[8],"instances":[10],"in":[11,21],"untrimmed":[12],"videos":[13],"with":[14],"only":[15],"video-level":[16],"supervision.":[17],"Despite":[18],"recent":[19],"advances":[20],"WTAL":[22,37,63,118],"methods,":[23],"achieving":[24],"accurate":[25],"boundary":[26],"remains":[28],"a":[29,40,123,142,208],"significant":[30],"challenge.":[31],"A":[32],"key":[33],"reason":[34],"is":[35],"that":[36,55,69,102,131,203],"networks":[38],"following":[39],"localization-by-classification":[41],"pipeline":[42],"tend":[43],"focus":[45,65],"on":[46,66,211],"the":[47,62,83,89,93,104,109,114,117,157,165,189,196,204],"most":[48],"discriminative":[49,105],"features,":[50,173],"neglecting":[51],"some":[52],"ambiguous":[53],"features":[54,68,101,107],"may":[56],"contain":[57],"instances.":[59],"To":[60,163],"make":[61],"model":[64,95,137],"low-discriminative":[67],"include":[70],"instances,":[72],"we":[73,121,140,174],"propose":[74,141],"an":[75,176],"action-to-action":[76],"diffusion":[77,90,94,136,143,166,197],"(ActionDiff)":[78],"network.":[79],"This":[80],"network":[81],"leverages":[82],"smoothness":[84],"of":[85,116,191],"data":[86],"generated":[87],"by":[88,151,156,195],"model,":[91],"using":[92],"output":[97],"smooth":[98],"and":[99,160,184,218],"high-quality":[100,147],"weaken":[103],"from":[108],"base":[110],"branch,":[111],"thereby":[112],"enhancing":[113],"performance":[115,210],"task.":[119],"First,":[120],"develop":[122],"topk-based":[124],"masking":[125],"strategy":[126,179],"generate":[128,146,170],"binary":[129],"masks":[130],"serve":[132],"as":[133],"pseudo-labels":[134,159],"for":[135],"learning.":[138],"Then,":[139],"branch":[144],"latent":[148],"space":[150],"iteratively":[152],"removing":[153],"noise":[154],"guided":[155],"designed":[158],"conditional":[161,178,182],"information.":[162],"enhance":[164],"branch's":[167],"capability":[168],"human":[171,192],"behavioral":[172],"design":[175],"action-related":[177],"obtain":[181],"information":[183],"use":[185],"it":[186],"guide":[188],"modeling":[190],"behavior":[193],"knowledge":[194],"branch.":[198],"Our":[199],"comprehensive":[200],"experiments":[201],"demonstrate":[202],"proposed":[205],"method":[206],"achieves":[207],"promising":[209],"three":[212],"benchmark":[213],"datasets:":[214],"THUMOS14,":[215],"ActivityNet":[216],"v1.2,":[217],"v1.3.":[219]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}