{"id":"https://openalex.org/W7154512807","doi":"https://doi.org/10.1145/3807956","title":"Semantic Prototype Guided Sparse Temporal Interaction for Weakly Supervised Temporal Action Localization","display_name":"Semantic Prototype Guided Sparse Temporal Interaction for Weakly Supervised Temporal Action Localization","publication_year":2026,"publication_date":"2026-04-15","ids":{"openalex":"https://openalex.org/W7154512807","doi":"https://doi.org/10.1145/3807956"},"language":"en","primary_location":{"id":"doi:10.1145/3807956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807956","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3807956","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jing Wang","orcid":"https://orcid.org/0000-0001-7962-4091"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7962-4091","affiliations":[{"raw_affiliation_string":"Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dehui Kong","orcid":"https://orcid.org/0000-0001-7722-7172"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehui Kong","raw_affiliation_strings":["Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7722-7172","affiliations":[{"raw_affiliation_string":"Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101612297","display_name":"Jinghua Li","orcid":"https://orcid.org/0000-0002-5583-8260"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghua Li","raw_affiliation_strings":["Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5583-8260","affiliations":[{"raw_affiliation_string":"Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075502576","display_name":"Xiaochen Wang","orcid":"https://orcid.org/0009-0002-4355-3169"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochen Wang","raw_affiliation_strings":["Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-4355-3169","affiliations":[{"raw_affiliation_string":"Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020527092","display_name":"Baocai Yin","orcid":"https://orcid.org/0000-0003-3121-1823"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baocai Yin","raw_affiliation_strings":["Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3121-1823","affiliations":[{"raw_affiliation_string":"Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210100255"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42766805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"6","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.973800003528595,"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":0.973800003528595,"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":0.005799999926239252,"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":0.00430000014603138,"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/action","display_name":"Action (physics)","score":0.6553999781608582},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6037999987602234},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5789999961853027},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5242000222206116},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3763999938964844},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.3756999969482422},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3614000082015991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8967000246047974},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6553999781608582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6337000131607056},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6037999987602234},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5789999961853027},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3034999966621399},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3807956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807956","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3807956","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807956","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.752828061580658}],"awards":[{"id":"https://openalex.org/G6077705658","display_name":null,"funder_award_id":"2021ZD0111902","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7964231441","display_name":null,"funder_award_id":"62172022, U21B2038, 62476179","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1578985305","https://openalex.org/W1927052826","https://openalex.org/W2336403884","https://openalex.org/W2546190447","https://openalex.org/W2946165673","https://openalex.org/W2963383024","https://openalex.org/W2963524571","https://openalex.org/W2964010806","https://openalex.org/W2998702159","https://openalex.org/W3035585099","https://openalex.org/W3150473382","https://openalex.org/W3207927851","https://openalex.org/W4225505766","https://openalex.org/W4308391676","https://openalex.org/W4313555695","https://openalex.org/W4321188367","https://openalex.org/W4372037321","https://openalex.org/W4385477922","https://openalex.org/W4386071527","https://openalex.org/W4386076495","https://openalex.org/W4386432237","https://openalex.org/W4387247666","https://openalex.org/W4387526084","https://openalex.org/W4387546363","https://openalex.org/W4390873021","https://openalex.org/W4391756006","https://openalex.org/W4391953443","https://openalex.org/W4393065859","https://openalex.org/W4393154133","https://openalex.org/W4393206831","https://openalex.org/W4396594800","https://openalex.org/W4402048694","https://openalex.org/W4402401350","https://openalex.org/W4402715820","https://openalex.org/W4402916549","https://openalex.org/W4403147829","https://openalex.org/W4403265038","https://openalex.org/W4404555281","https://openalex.org/W4404645968","https://openalex.org/W4405566602","https://openalex.org/W4407688408","https://openalex.org/W4407949554","https://openalex.org/W4409262103"],"related_works":[],"abstract_inverted_index":{"Weakly":[0],"supervised":[1],"temporal":[2,54,105,123,151],"action":[3,9,35,46,75,89,132,182],"localization":[4],"(WTAL)":[5],"aims":[6],"to":[7,48,65,72,98,110,126,164],"detect":[8],"segments":[10,47],"in":[11,33],"untrimmed":[12],"videos":[13,78],"only":[14],"using":[15],"video-level":[16],"labels.":[17],"Existing":[18],"methods":[19],"typically":[20],"follow":[21],"the":[22,38,70,122],"multi-instance":[23],"learning":[24],"(MIL)":[25],"paradigm":[26],"with":[27],"a":[28,103,146,156],"top-k":[29],"strategy,":[30],"often":[31],"resulting":[32],"incomplete":[34],"localization.":[36,183],"Moreover,":[37,102],"local":[39],"and":[40,51,79,115,136,172,180],"discontinuous":[41],"nature":[42],"of":[43],"actions":[44],"causes":[45],"be":[49],"isolated":[50],"lack":[52],"sufficient":[53],"interaction.":[55],"To":[56],"address":[57],"these":[58],"issues,":[59],"this":[60,143],"article":[61,144],"introduces":[62],"semantic":[63,129,147,162],"prototypes":[64],"enrich":[66],"video":[67,158],"representations,":[68],"enabling":[69],"model":[71,112],"aggregate":[73],"category-level":[74],"cues":[76],"across":[77],"recover":[80],"semantically":[81],"relevant":[82],"but":[83],"weakly":[84],"activated":[85],"segments,":[86],"thereby":[87],"improving":[88],"completeness.":[90],"A":[91],"prototype":[92,148],"contrastive":[93],"loss":[94,120],"is":[95,108],"further":[96],"employed":[97],"improve":[99],"feature":[100],"discriminability.":[101],"sparse":[104,150],"interaction":[106,124,152],"unit":[107],"designed":[109],"jointly":[111],"short-term":[113],"context":[114],"long-range":[116],"dependencies.":[117],"The":[118],"boundary-guided":[119],"utilizes":[121],"outputs":[125],"explicitly":[127],"constrain":[128],"responses":[130],"around":[131],"boundaries,":[133],"promoting":[134],"sharp":[135],"temporally":[137],"consistent":[138],"transitions.":[139],"Based":[140],"on":[141,170],"these,":[142],"proposes":[145],"guided":[149],"network":[153],"(S2Net),":[154],"achieving":[155],"unified":[157],"modeling":[159],"from":[160],"full":[161],"understanding":[163],"fine-grained":[165],"boundary":[166],"perception.":[167],"Extensive":[168],"experiments":[169],"THUMOS14":[171],"ActivityNet1.3":[173],"demonstrate":[174],"that":[175],"S2Net":[176],"achieves":[177],"more":[178],"accurate":[179],"complete":[181]},"counts_by_year":[],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2026-04-16T00:00:00"}