{"id":"https://openalex.org/W4403899609","doi":"https://doi.org/10.1145/3696409.3700211","title":"Action Selection Learning for Multi-label Multi-view Action Recognition","display_name":"Action Selection Learning for Multi-label Multi-view Action Recognition","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4403899609","doi":"https://doi.org/10.1145/3696409.3700211"},"language":"en","primary_location":{"id":"doi:10.1145/3696409.3700211","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696409.3700211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.03302","any_repository_has_fulltext":true},"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":[],"countries":[],"is_corresponding":true,"raw_author_name":"Trung Thanh Nguyen","raw_affiliation_strings":["Nagoya Univeristy, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya Univeristy, Nagoya, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027960360","display_name":"Yasutomo Kawanishi","orcid":"https://orcid.org/0000-0002-3799-4550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasutomo Kawanishi","raw_affiliation_strings":["RIKEN, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN, Kyoto, Japan","institution_ids":[]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, 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"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101718798"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5107,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84340149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9970999956130981,"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":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.8451031446456909},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6832979321479797},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.6462646722793579},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5764667391777039},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.5638388395309448},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5032674670219421},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.47372809052467346},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.44822293519973755},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4453328251838684},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43596720695495605},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4197664260864258},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4141704738140106},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4135282635688782},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38212522864341736},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.09070903062820435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8451031446456909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6832979321479797},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.6462646722793579},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5764667391777039},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.5638388395309448},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5032674670219421},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.47372809052467346},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.44822293519973755},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4453328251838684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43596720695495605},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4197664260864258},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4141704738140106},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4135282635688782},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38212522864341736},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.09070903062820435},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3696409.3700211","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696409.3700211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.03302","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.03302","pdf_url":"https://arxiv.org/pdf/2410.03302","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.03302","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.03302","pdf_url":"https://arxiv.org/pdf/2410.03302","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.41999998688697815,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G5266459512","display_name":null,"funder_award_id":"JP21H03519","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8079321836","display_name":"Scene Understanding and Knowledge Extension by Active Open-world Recognition","funder_award_id":"24H00733","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403899609.pdf","grobid_xml":"https://content.openalex.org/works/W4403899609.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W54887220","https://openalex.org/W1583837637","https://openalex.org/W2194775991","https://openalex.org/W2292288263","https://openalex.org/W2560886373","https://openalex.org/W2810685774","https://openalex.org/W2897426518","https://openalex.org/W2944006115","https://openalex.org/W2963282966","https://openalex.org/W2964134613","https://openalex.org/W2981965938","https://openalex.org/W2990503944","https://openalex.org/W3011934803","https://openalex.org/W3013318875","https://openalex.org/W3081706233","https://openalex.org/W3088102655","https://openalex.org/W3091422730","https://openalex.org/W3104432418","https://openalex.org/W3132736751","https://openalex.org/W3138697035","https://openalex.org/W3158576998","https://openalex.org/W3172990466","https://openalex.org/W3175580044","https://openalex.org/W3195949276","https://openalex.org/W3197341423","https://openalex.org/W3199934435","https://openalex.org/W4214612132","https://openalex.org/W4221155627","https://openalex.org/W4231611928","https://openalex.org/W4291906424","https://openalex.org/W4304098269","https://openalex.org/W4312290604","https://openalex.org/W4319300928","https://openalex.org/W4386038358","https://openalex.org/W4386076580","https://openalex.org/W4389819138","https://openalex.org/W4390190427"],"related_works":["https://openalex.org/W2385368906","https://openalex.org/W2902924992","https://openalex.org/W2626642044","https://openalex.org/W93537448","https://openalex.org/W2619807045","https://openalex.org/W2388758053","https://openalex.org/W2949734191","https://openalex.org/W2017333877","https://openalex.org/W2048332520","https://openalex.org/W2295006769"],"abstract_inverted_index":{"Multi-label":[0],"multi-view":[1,24],"action":[2,25,42,83,143],"recognition":[3,26],"aims":[4],"to":[5,58,86,109,136,164],"recognize":[6],"multiple":[7,17],"concurrent":[8],"or":[9],"sequential":[10],"actions":[11],"from":[12,96,115,130],"untrimmed":[13],"videos":[14],"captured":[15],"by":[16,90],"cameras.":[18],"Existing":[19],"work":[20],"has":[21],"focused":[22],"on":[23,51],"in":[27,146],"a":[28,60,103,147],"narrow":[29],"area":[30,62],"with":[31,63],"strong":[32],"labels":[33,66,132],"available,":[34],"where":[35,54],"the":[36,46,69,73,92,124,134,138,152,156,160],"onset":[37],"and":[38,112],"offset":[39],"of":[40,159],"each":[41],"are":[43,56],"labeled":[44],"at":[45,68,123,133,172],"frame-level.":[47],"This":[48],"study":[49],"focuses":[50],"real-world":[52,148],"scenarios":[53],"cameras":[55],"distributed":[57],"capture":[59],"wide-range":[61],"only":[64],"weak":[65,131],"available":[67,171],"video-level.":[70],"We":[71],"propose":[72],"method":[74,101,162],"named":[75],"Multi-view":[76,104],"Action":[77,118],"Selection":[78,119],"Learning":[79,120],"(MultiASL),":[80],"which":[81],"leverages":[82],"selection":[84],"learning":[85],"enhance":[87],"view":[88],"fusion":[89],"selecting":[91],"most":[93,139],"useful":[94],"information":[95],"different":[97],"viewpoints.":[98],"The":[99,167],"proposed":[100,161],"includes":[102],"Spatial-Temporal":[105],"Transformer":[106],"video":[107],"encoder":[108],"extract":[110],"spatial":[111],"temporal":[113],"features":[114],"multi-viewpoint":[116],"videos.":[117],"is":[121,170],"employed":[122],"frame-level,":[125],"using":[126,151],"pseudo":[127],"ground-truth":[128],"obtained":[129],"video-level,":[135],"identify":[137],"relevant":[140],"frames":[141],"for":[142],"recognition.":[144],"Experiments":[145],"office":[149],"environment":[150],"MM-Office":[153],"dataset":[154],"demonstrate":[155],"superior":[157],"performance":[158],"compared":[163],"existing":[165],"methods.":[166],"source":[168],"code":[169],"https://github.com/thanhhff/MultiASL/.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}