{"id":"https://openalex.org/W3205691536","doi":"https://doi.org/10.1145/3474085.3475472","title":"Counterfactual Debiasing Inference for Compositional Action Recognition","display_name":"Counterfactual Debiasing Inference for Compositional Action Recognition","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205691536","doi":"https://doi.org/10.1145/3474085.3475472","mag":"3205691536"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475472","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-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/A5102605009","display_name":"Pengzhan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengzhan Sun","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059368105","display_name":"Bo Wu","orcid":"https://orcid.org/0000-0001-6658-6452"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Wu","raw_affiliation_strings":["MIT-IBM Watson AI Lab, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017473451","display_name":"Xunsong Li","orcid":"https://orcid.org/0009-0009-5803-6691"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunsong Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719271","display_name":"Wen Li","orcid":"https://orcid.org/0000-0002-5559-8594"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080093489","display_name":"Lixin Duan","orcid":"https://orcid.org/0000-0002-0723-4016"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixin Duan","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040877128","display_name":"Chuang Gan","orcid":"https://orcid.org/0000-0003-4031-5886"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuang Gan","raw_affiliation_strings":["MIT-IBM Watson AI Lab, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3584,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.83324463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3220","last_page":"3228"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9944000244140625,"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/debiasing","display_name":"Debiasing","score":0.9299225211143494},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.8872434496879578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7786290645599365},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7546533942222595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7149431705474854},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5597483515739441},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.53604656457901},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5085245370864868},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5029436945915222},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.47823041677474976},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4523426592350006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41766995191574097},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.1566082239151001},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14442428946495056},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12189698219299316}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.9299225211143494},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8872434496879578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7786290645599365},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7546533942222595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7149431705474854},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5597483515739441},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.53604656457901},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5085245370864868},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5029436945915222},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.47823041677474976},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4523426592350006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41766995191574097},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.1566082239151001},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14442428946495056},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12189698219299316},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475472","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1900913856","https://openalex.org/W1947481528","https://openalex.org/W2105934661","https://openalex.org/W2122413656","https://openalex.org/W2252355370","https://openalex.org/W2469228190","https://openalex.org/W2507009361","https://openalex.org/W2514167171","https://openalex.org/W2599765304","https://openalex.org/W2625366777","https://openalex.org/W2736596806","https://openalex.org/W2806331055","https://openalex.org/W2808675313","https://openalex.org/W2890234836","https://openalex.org/W2895243423","https://openalex.org/W2903571680","https://openalex.org/W2927257531","https://openalex.org/W2955874753","https://openalex.org/W2962899219","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963352593","https://openalex.org/W2963524571","https://openalex.org/W2963699792","https://openalex.org/W2987123286","https://openalex.org/W2990503944","https://openalex.org/W2992308087","https://openalex.org/W3000279895","https://openalex.org/W3008613063","https://openalex.org/W3034257141","https://openalex.org/W3034679267","https://openalex.org/W3035017890","https://openalex.org/W3035103424","https://openalex.org/W3035517717","https://openalex.org/W3093455342","https://openalex.org/W3104218139","https://openalex.org/W3107646798","https://openalex.org/W3111098292","https://openalex.org/W3145915828","https://openalex.org/W3150679290","https://openalex.org/W3177934633","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4362554880","https://openalex.org/W4386875279","https://openalex.org/W4281684980","https://openalex.org/W2171721708","https://openalex.org/W3214527415","https://openalex.org/W4287887864","https://openalex.org/W1495104519","https://openalex.org/W4390963114","https://openalex.org/W4321276883","https://openalex.org/W4388144300"],"abstract_inverted_index":{"Compositional":[0],"action":[1,63,104,198],"recognition":[2],"is":[3,147],"a":[4,72,115,159],"novel":[5,73],"challenge":[6],"in":[7,28,67,103,114,149],"the":[8,16,83,89,100,109,128,150,154,166,170,175,178,184,202,209,214],"computer":[9],"vision":[10],"community":[11],"and":[12,21,106,123,136,164],"focuses":[13],"on":[14,208],"revealing":[15],"different":[17],"combinations":[18],"of":[19,24,95,111,177,183,204,216],"verbs":[20],"nouns":[22],"instead":[23],"treating":[25],"subject-object":[26],"interactions":[27],"videos":[29],"as":[30],"individual":[31],"instances":[32,199],"only.":[33],"Existing":[34],"methods":[35],"tackle":[36],"this":[37,68],"challenging":[38],"task":[39],"by":[40,87,92,131,169,173,200],"simply":[41],"ignoring":[42],"appearance":[43,101,134,145,171],"information":[44,102,113,135,146,172],"or":[45],"fusing":[46],"object":[47],"appearances":[48,94],"with":[49,144],"dynamic":[50],"instance":[51],"tracklets.":[52],"However,":[53],"those":[54],"strategies":[55],"usually":[56],"do":[57],"not":[58],"perform":[59],"well":[60],"for":[61],"unseen":[62,197],"instances.":[64],"For":[65],"that,":[66,189],"work":[69],"we":[70,120,157],"propose":[71],"learning":[74],"framework":[75],"called":[76],"Counterfactual":[77],"Debiasing":[78],"Network":[79],"(CDN)":[80],"to":[81,126],"improve":[82],"model":[84,127],"generalization":[85],"ability":[86],"removing":[88],"interference":[90],"introduced":[91,168],"visual":[93],"objects/subjects.":[96],"It":[97],"explicitly":[98],"learns":[99],"representations":[105],"later":[107],"removes":[108,165],"effect":[110,203],"such":[112],"causal":[116,160],"inference":[117,130,180],"manner.":[118],"Specifically,":[119],"use":[121],"tracklets":[122],"video":[124,142],"content":[125,143],"factual":[129,185],"considering":[132],"both":[133],"structure":[137],"information.":[138],"In":[139],"contrast,":[140],"only":[141],"leveraged":[148],"counterfactual":[151,179],"inference.":[152,186],"With":[153],"two":[155],"inferences,":[156],"conduct":[158],"graph":[161],"which":[162],"captures":[163],"bias":[167],"subtracting":[174],"result":[176],"from":[181],"that":[182],"By":[187],"doing":[188],"our":[190,217],"proposed":[191,218],"CDN":[192,219],"method":[193],"can":[194],"better":[195],"recognize":[196],"debiasing":[201],"appearances.":[205],"Extensive":[206],"experiments":[207],"Something-Else":[210],"dataset":[211],"clearly":[212],"show":[213],"effectiveness":[215],"over":[220],"existing":[221],"state-of-the-art":[222],"methods.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}