{"id":"https://openalex.org/W7130859014","doi":"https://doi.org/10.1007/s11263-026-02738-x","title":"An Effective-Efficient Approach for Dense Multi-Label Action Detection","display_name":"An Effective-Efficient Approach for Dense Multi-Label Action Detection","publication_year":2026,"publication_date":"2026-02-21","ids":{"openalex":"https://openalex.org/W7130859014","doi":"https://doi.org/10.1007/s11263-026-02738-x"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-026-02738-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02738-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02738-x.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","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/s11263-026-02738-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126556405","display_name":"Faegheh Sardari","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Faegheh Sardari","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK"],"raw_orcid":"https://orcid.org/0000-0002-9134-0427","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075260187","display_name":"Armin Mustafa","orcid":"https://orcid.org/0000-0002-1779-2775"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Armin Mustafa","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123887817","display_name":"Philip J. B. Jackson","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip J. B. Jackson","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126530169","display_name":"Adrian Hilton","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adrian Hilton","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5126556405"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26138463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":"3","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":0.7382000088691711,"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":0.7382000088691711,"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":0.11819999665021896,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.02329999953508377,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6521000266075134},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.6363999843597412},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6050000190734863},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5077999830245972},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44690001010894775},{"id":"https://openalex.org/keywords/temporal-database","display_name":"Temporal database","score":0.37290000915527344},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3310000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289999723434448},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6521000266075134},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6150000095367432},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6050000190734863},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5077999830245972},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3846000134944916},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3248000144958496},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.272599995136261}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-026-02738-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02738-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02738-x.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-026-02738-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02738-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02738-x.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.41389554738998413,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1065596782","display_name":"Audio-Visual Media Research Platform","funder_award_id":"EP/P022529/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3480456763","display_name":null,"funder_award_id":"EP/P022529","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7063807409","display_name":"BBC Prosperity Partnership: Future Personalised Object-Based Media Experiences Delivered at Scale Anywhere","funder_award_id":"EP/V038087/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7130859014.pdf","grobid_xml":"https://content.openalex.org/works/W7130859014.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2292288263","https://openalex.org/W2337252826","https://openalex.org/W2904083233","https://openalex.org/W2962677524","https://openalex.org/W2962876901","https://openalex.org/W2963247196","https://openalex.org/W2963524571","https://openalex.org/W2963874033","https://openalex.org/W2963925437","https://openalex.org/W2964189376","https://openalex.org/W2964274041","https://openalex.org/W3034572008","https://openalex.org/W3096609285","https://openalex.org/W3120364173","https://openalex.org/W3132607382","https://openalex.org/W3175078602","https://openalex.org/W3175357208","https://openalex.org/W3176212189","https://openalex.org/W3202003978","https://openalex.org/W4214673031","https://openalex.org/W4226270831","https://openalex.org/W4312508181","https://openalex.org/W4312693115","https://openalex.org/W4313171426","https://openalex.org/W4390190264","https://openalex.org/W4390872764","https://openalex.org/W4390873541","https://openalex.org/W4402351152","https://openalex.org/W4402704603","https://openalex.org/W4402727982","https://openalex.org/W4402753830","https://openalex.org/W4402753952","https://openalex.org/W4402753985","https://openalex.org/W4411245215"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Unlike":[1],"the":[2,59,71,101,137,214,233,244,269,272],"sparse":[3],"label":[4],"action":[5,11,41,51,79,110,174],"detection":[6],"task,":[7,32],"where":[8],"a":[9,17,20,90,95,185,192],"single":[10],"occurs":[12],"in":[13,19,140,156,208],"each":[14],"timestamp":[15],"of":[16,164,199,216,271,275],"video,":[18],"dense":[21,223],"multi-label":[22,224],"scenario,":[23],"actions":[24],"can":[25,159],"overlap":[26],"temporally.":[27],"To":[28],"address":[29,180],"this":[30,83,87,151,168,177,181],"challenging":[31,222],"it":[33],"is":[34,170],"necessary":[35],"to":[36,74,103,122,161,267],"simultaneously":[37],"learn":[38],"(i)":[39],"co-occurrence":[40,50,109],"relationships":[42,52],"and":[43,202,227,239,246,258],"(ii)":[44],"temporal":[45,108,124,130,144,200],"dependencies.":[46],"Current":[47],"methods":[48],"model":[49,123],"by":[53,88,183,237],"explicitly":[54,106],"embedding":[55],"class":[56,80],"relations":[57],"into":[58],"transformer":[60,187,210],"network":[61,72,102,188],"architecture.":[62],"However,":[63,136],"these":[64],"approaches":[65,127],"are":[66],"not":[67],"computationally":[68],"efficient,":[69],"as":[70],"needs":[73],"compute":[75],"all":[76],"possible":[77],"pair":[78],"relations.":[81],"In":[82,176],"paper,":[84,178],"we":[85,179],"overcome":[86],"introducing":[89],"novel":[91,96,186],"framework":[92],"trained":[93],"through":[94,132],"learning":[97],"paradigm":[98],"that":[99,149,189,229],"allows":[100],"benefit":[104],"from":[105],"modelling":[107,196],"dependencies":[111,201],"during":[112,119],"training":[113],"without":[114],"imposing":[115],"their":[116],"computational":[117],"overhead":[118],"inference.":[120],"Furthermore,":[121],"information,":[125],"recent":[126],"extract":[128],"multi-scale":[129],"features":[131],"hierarchical":[133,157],"transformer-based":[134],"networks.":[135],"self-attention":[138],"mechanism":[139],"transformers":[141],"inherently":[142],"loses":[143],"positional":[145,165,206],"information.":[146,166],"We":[147,212,261],"argue":[148],"combining":[150],"with":[152],"multiple":[153],"sub-sampling":[154],"processes":[155],"designs":[158],"lead":[160],"further":[162],"loss":[163],"Preserving":[167],"information":[169],"essential":[171],"for":[172],"accurate":[173],"detection.":[175],"issue":[182],"proposing":[184],"(a)":[190],"employs":[191],"non-hierarchical":[193],"structure":[194],"when":[195],"different":[197,273],"ranges":[198],"(b)":[203],"embeds":[204],"relative":[205],"encoding":[207],"its":[209],"layers.":[211],"evaluate":[213],"performance":[215],"our":[217,230,276],"proposed":[218,277],"approach":[219],"on":[220,243],"two":[221],"benchmark":[225],"datasets":[226],"show":[228],"method":[231],"improves":[232],"current":[234],"state-of-the-art":[235,252],"results":[236,255],"1.1%":[238],"0.6%":[240],"per-frame":[241,253],"mAP":[242,254],"Charades":[245],"MultiTHUMOS":[247],"datasets,":[248],"respectively,":[249],"achieving":[250],"new":[251],"at":[256],"26.5%":[257],"44.6%,":[259],"respectively.":[260],"also":[262],"performed":[263],"extensive":[264],"ablation":[265],"studies":[266],"examine":[268],"impact":[270],"components":[274],"approach.":[278],"Our":[279],"code":[280],"will":[281],"be":[282],"released":[283],"upon":[284],"paper":[285],"publication":[286]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-22T00:00:00"}