{"id":"https://openalex.org/W4379986307","doi":"https://doi.org/10.1145/3603253","title":"Attentional Composition Networks for Long-Tailed Human Action Recognition","display_name":"Attentional Composition Networks for Long-Tailed Human Action Recognition","publication_year":2023,"publication_date":"2023-06-09","ids":{"openalex":"https://openalex.org/W4379986307","doi":"https://doi.org/10.1145/3603253"},"language":"en","primary_location":{"id":"doi:10.1145/3603253","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603253","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/A5100324809","display_name":"Haoran Wang","orcid":"https://orcid.org/0000-0001-6350-5645"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Wang","raw_affiliation_strings":["Northeastern University, China"],"raw_orcid":"https://orcid.org/0000-0001-6350-5645","affiliations":[{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455429","display_name":"Yajie Wang","orcid":"https://orcid.org/0009-0005-8792-6088"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yajie Wang","raw_affiliation_strings":["Northeastern University, China"],"raw_orcid":"https://orcid.org/0009-0005-8792-6088","affiliations":[{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085309099","display_name":"Baosheng Yu","orcid":"https://orcid.org/0000-0002-0761-7893"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Baosheng Yu","raw_affiliation_strings":["The University of Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0761-7893","affiliations":[{"raw_affiliation_string":"The University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074672983","display_name":"Yibing Zhan","orcid":"https://orcid.org/0000-0003-3180-0484"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibing Zhan","raw_affiliation_strings":["JD Explore Academy, China"],"raw_orcid":"https://orcid.org/0000-0003-3180-0484","affiliations":[{"raw_affiliation_string":"JD Explore Academy, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005377211","display_name":"Chunfeng Yuan","orcid":"https://orcid.org/0000-0003-2219-4961"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunfeng Yuan","raw_affiliation_strings":["Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0003-2219-4961","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100748706","display_name":"Wankou Yang","orcid":"https://orcid.org/0000-0002-6385-6776"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wankou Yang","raw_affiliation_strings":["Southeast University, China"],"raw_orcid":"https://orcid.org/0000-0002-6385-6776","affiliations":[{"raw_affiliation_string":"Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5318,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65647334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"20","issue":"1","first_page":"1","last_page":"18"},"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":0.9939000010490417,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9912999868392944,"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/computer-science","display_name":"Computer science","score":0.6560673713684082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5953625440597534},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5936099290847778},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5749374032020569},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5452544689178467},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.525306761264801},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.5139614939689636},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4854329228401184},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45160093903541565},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4502998888492584},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4140547811985016},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3384368121623993},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11685815453529358}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6560673713684082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5953625440597534},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5936099290847778},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5749374032020569},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5452544689178467},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.525306761264801},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.5139614939689636},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4854329228401184},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45160093903541565},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4502998888492584},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4140547811985016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3384368121623993},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11685815453529358},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3603253","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603253","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":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1115950578","display_name":null,"funder_award_id":"N2304012","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2898152415","display_name":null,"funder_award_id":"62002090","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3749818891","display_name":null,"funder_award_id":"61773117, 61972397, 62276061, 62002090","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G782967413","display_name":null,"funder_award_id":"62276061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8108323439","display_name":"\u57fa\u4e8eRGB-D\u89c6\u9891\u7684\u591a\u6a21\u6001\u4eba\u4f53\u884c\u4e3a\u8bc6\u522b\u7814\u7a76","funder_award_id":"61972397","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8812960752","display_name":null,"funder_award_id":"61773117","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522734439","https://openalex.org/W1941659294","https://openalex.org/W1983364832","https://openalex.org/W2077069816","https://openalex.org/W2118978333","https://openalex.org/W2142694332","https://openalex.org/W2169393274","https://openalex.org/W2186222003","https://openalex.org/W2342662179","https://openalex.org/W2440599146","https://openalex.org/W2559655401","https://openalex.org/W2607408136","https://openalex.org/W2612690371","https://openalex.org/W2619947201","https://openalex.org/W2767106145","https://openalex.org/W2770804203","https://openalex.org/W2883429621","https://openalex.org/W2914393402","https://openalex.org/W2942750779","https://openalex.org/W2963091558","https://openalex.org/W2963820951","https://openalex.org/W2964080601","https://openalex.org/W2990152177","https://openalex.org/W2999905431","https://openalex.org/W3214094165","https://openalex.org/W4214920941","https://openalex.org/W4214923132","https://openalex.org/W4234552385","https://openalex.org/W4281749424","https://openalex.org/W4281752744","https://openalex.org/W4301409532","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2153749698","https://openalex.org/W2163511125","https://openalex.org/W2356312238","https://openalex.org/W2610352806","https://openalex.org/W2886496229","https://openalex.org/W2243424819","https://openalex.org/W2350402522","https://openalex.org/W2314879657","https://openalex.org/W2507540959","https://openalex.org/W4287181611"],"abstract_inverted_index":{"The":[0],"problem":[1,16],"of":[2,113,200],"long-tailed":[3,14],"visual":[4,21],"recognition":[5,164,182],"has":[6],"been":[7],"receiving":[8],"increasing":[9],"research":[10],"attention.":[11],"However,":[12],"the":[13,63,67,72,75,91,103,119,123,127,153,156,162,170,194,198,201,217],"distribution":[15],"remains":[17],"underexplored":[18],"for":[19,37,62,74,145,155,165,204],"video-based":[20,38],"recognition.":[22,41,213],"To":[23,168],"address":[24],"this":[25,28],"issue,":[26],"in":[27,66,122,210],"article":[29],"we":[30,81,150,175],"propose":[31],"a":[32,87,111,178],"compositional":[33,171],"learning":[34],"based":[35],"solution":[36],"human":[39,172,180,211],"action":[40,84,109,163,173,181,212],"Our":[42],"method,":[43],"named":[44],"Attentional":[45],"Composition":[46],"Networks":[47],"(ACN),":[48],"first":[49],"learns":[50],"verb-like":[51],"and":[52,115,129,159,193,207,216],"preposition-like":[53],"components,":[54],"then":[55],"shuffles":[56],"these":[57,166],"components":[58],"to":[59,70,106,141],"generate":[60],"samples":[61],"tail":[64,76,146,157],"classes":[65,158],"feature":[68,143],"space":[69],"augment":[71],"data":[73,154],"classes.":[77,147,167],"Specifically,":[78],"during":[79],"training,":[80],"represent":[82],"each":[83,108],"video":[85],"by":[86],"graph":[88],"that":[89],"captures":[90],"spatial-temporal":[92],"relations":[93],"(edges)":[94],"among":[95],"detected":[96],"human/object":[97],"instances":[98],"(nodes).":[99],"Then,":[100],"ACN":[101],"utilizes":[102],"position":[104],"information":[105],"decompose":[107],"into":[110],"set":[112],"verb":[114,128],"preposition":[116,130],"representations":[117,144],"using":[118],"edge":[120],"features":[121,131],"graph.":[124],"After":[125],"that,":[126],"from":[132],"different":[133],"videos":[134],"are":[135,220],"combined":[136],"via":[137],"an":[138],"attention":[139],"structure":[140],"synthesize":[142],"This":[148],"way,":[149],"can":[151],"enrich":[152],"consequently":[160],"improve":[161],"evaluate":[169],"recognition,":[174],"further":[176],"contribute":[177],"new":[179],"dataset,":[183],"namely":[184],"NEU-Interaction":[185],"(NEU-I).":[186],"Experimental":[187],"results":[188],"on":[189],"both":[190],"Something-Something":[191],"V2":[192],"proposed":[195,202],"NEU-I":[196,218],"demonstrate":[197],"effectiveness":[199],"method":[203],"long-tailed,":[205],"few-shot,":[206],"zero-shot":[208],"problems":[209],"Source":[214],"code":[215],"dataset":[219],"available":[221],"at":[222],"https://github.com/YajieW99/ACN":[223],".":[224]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}