{"id":"https://openalex.org/W4415702051","doi":"https://doi.org/10.1145/3773986","title":"Hierarchical Global\u2013Local Fusion for One-stage Open-vocabulary Temporal Action Detection","display_name":"Hierarchical Global\u2013Local Fusion for One-stage Open-vocabulary Temporal Action Detection","publication_year":2025,"publication_date":"2025-10-30","ids":{"openalex":"https://openalex.org/W4415702051","doi":"https://doi.org/10.1145/3773986"},"language":"en","primary_location":{"id":"doi:10.1145/3773986","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3773986","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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101718798","display_name":"Trung Th\u00e0nh Nguy\u1ec5n","orcid":"https://orcid.org/0000-0001-8976-2922"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Trung Thanh Nguyen","raw_affiliation_strings":["Nagoya University, Nagoya, Japan and RIKEN, Kyoto, Japan","Graduate School of Informatics, Nagoya University, Japan and Guardian Robot Project, Information R&D and Strategy Headquarters, RIKEN, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8976-2922","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan and RIKEN, Kyoto, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Japan and Guardian Robot Project, Information R&D and Strategy Headquarters, RIKEN, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027960360","display_name":"Yasutomo Kawanishi","orcid":"https://orcid.org/0000-0002-3799-4550"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasutomo Kawanishi","raw_affiliation_strings":["RIKEN, Kyoto, Japan and Nagoya University, Nagoya, Japan","Guardian Robot Project, Information R&D and Strategy Headquarters, RIKEN, Japan and Center for Artificial Intelligence, Mathematical and Data Science, Nagoya University, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3799-4550","affiliations":[{"raw_affiliation_string":"RIKEN, Kyoto, Japan and Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Guardian Robot Project, Information R&D and Strategy Headquarters, RIKEN, Japan and Center for Artificial Intelligence, Mathematical and Data Science, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047823141","display_name":"Takahiro Komamizu","orcid":"https://orcid.org/0000-0002-3041-4330"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Komamizu","raw_affiliation_strings":["Nagoya University, Nagoya, Japan","Center for Artificial Intelligence, Mathematical and Data Science and Graduate School of Informatics, Nagoya University, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3041-4330","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Center for Artificial Intelligence, Mathematical and Data Science and Graduate School of Informatics, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034941095","display_name":"Ichiro Ide","orcid":"https://orcid.org/0000-0003-3942-9296"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ichiro Ide","raw_affiliation_strings":["Nagoya University, Nagoya, Japan","Graduate School of Informatics and Center for Artificial Intelligence, Mathematical and Data Science, Nagoya University, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3942-9296","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Informatics and Center for Artificial Intelligence, Mathematical and Data Science, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76590199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"1","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.900600016117096,"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":0.900600016117096,"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":0.05270000174641609,"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/T11431","display_name":"Action Observation and Synchronization","score":0.014999999664723873,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6209999918937683},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5738999843597412},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5521000027656555},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.489300012588501},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4724999964237213},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4336000084877014},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3662000000476837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.866599977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6966000199317932},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6209999918937683},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5738999843597412},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5521000027656555},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4724999964237213},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39500001072883606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.35249999165534973},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3151000142097473},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3109000027179718},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.26750001311302185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773986","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3773986","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":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1561586533","display_name":null,"funder_award_id":"JP21H03519 and JP24H00733","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2336403884","https://openalex.org/W2896348597","https://openalex.org/W2963315828","https://openalex.org/W3173459793","https://openalex.org/W4206584175","https://openalex.org/W4285606530","https://openalex.org/W4396594800","https://openalex.org/W4399601498"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"Temporal":[1,12,145],"Action":[2,13],"Detection":[3,14],"(Open-vocab":[4],"TAD)":[5,16],"extends":[6],"the":[7,27,55,60,64,88,111,119,174,178,191,199,210],"detection":[8,66],"scope":[9],"of":[10,95,124,142,170,212,224],"Closed-vocabulary":[11],"(Closed-vocab":[15],"to":[17,76,93,101,117,159,208],"unseen":[18,188,225],"action":[19,45,104,125,235],"classes":[20],"specified":[21],"by":[22],"vocabularies":[23],"not":[24],"included":[25],"in":[26,54,190,219,243],"training":[28],"data,":[29],"within":[30],"untrimmed":[31],"video.":[32],"Typical":[33],"Open-vocab":[34,138,192],"TAD":[35,139],"methods":[36,70],"adopt":[37],"a":[38,133,167,221],"two-stage":[39],"approach":[40,135],"that":[41],"first":[42,56],"proposes":[43],"candidate":[44],"intervals":[46],"and":[47,63,121,149,162,182,195,204,233,245],"then":[48],"identifies":[49],"those":[50],"actions.":[51,226],"However,":[52],"errors":[53],"stage":[57,62],"can":[58,91],"affect":[59],"subsequent":[61],"final":[65],"results.":[67],"Moreover,":[68],"conventional":[69],"for":[71,185],"temporal":[72,164,171],"context":[73,90,113],"analyses":[74],"tend":[75],"focus":[77],"solely":[78,86],"on":[79,87,110],"either":[80],"global":[81,89,161],"or":[82],"local":[83,112,163],"context.":[84],"Focusing":[85],"lead":[92],"lack":[94],"momentary":[96],"detail,":[97],"making":[98],"it":[99,115],"difficult":[100],"distinguish":[102],"one":[103],"from":[105],"another.":[106],"Conversely,":[107],"focusing":[108],"only":[109],"makes":[114],"challenging":[116],"determine":[118],"start":[120],"end":[122],"timings":[123],"intervals.":[126],"To":[127],"address":[128],"these":[129],"challenges,":[130],"we":[131],"introduce":[132],"one-stage":[134],"named":[136],"Hierarchical":[137,156],"(HOTAD),":[140],"consisting":[141],"two":[143],"branches:":[144],"Context":[146],"Analysis":[147],"(TCA)":[148],"Video\u2013Text":[150],"Alignment":[151],"(VTA).":[152],"The":[153,214],"former":[154],"utilizes":[155],"Encoder":[157],"(HE)":[158],"fuse":[160],"features,":[165],"enabling":[166],"comprehensive":[168],"capture":[169],"actions,":[172],"while":[173],"latter":[175],"branch":[176],"exploits":[177],"synergy":[179],"between":[180],"visual":[181],"textual":[183],"modalities":[184],"precisely":[186],"detecting":[187,220],"actions":[189],"setting.":[193],"Experiments":[194],"in-depth":[196],"analysis":[197],"using":[198],"widely":[200],"recognized":[201],"datasets":[202],"THUMOS14":[203],"ActivityNet-1.3":[205],"are":[206],"performed":[207],"show":[209],"effectiveness":[211],"HOTAD.":[213],"results":[215],"highlight":[216],"remarkable":[217],"accuracy":[218],"wide":[222],"range":[223],"Furthermore,":[227],"HOTAD":[228],"significantly":[229],"reduces":[230],"wrong":[231],"labels":[232],"localizes":[234],"instances":[236],"with":[237],"high":[238],"precision,":[239],"showcasing":[240],"its":[241],"robustness":[242],"complex":[244],"dynamic":[246],"video":[247],"settings.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-30T00:00:00"}