{"id":"https://openalex.org/W4402780967","doi":"https://doi.org/10.1109/cvpr52733.2024.01764","title":"Uncertainty-aware Action Decoupling Transformer for Action Anticipation","display_name":"Uncertainty-aware Action Decoupling Transformer for Action Anticipation","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402780967","doi":"https://doi.org/10.1109/cvpr52733.2024.01764"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5013851564","display_name":"Hongji Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongji Guo","raw_affiliation_strings":["Rensselaer Polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073021106","display_name":"Nakul Agarwal","orcid":"https://orcid.org/0000-0002-7684-6075"},"institutions":[{"id":"https://openalex.org/I4210145184","display_name":"Honda (United States)","ror":"https://ror.org/04vdmc602","country_code":"US","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210145184"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nakul Agarwal","raw_affiliation_strings":["Honda Research Institute,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute,USA","institution_ids":["https://openalex.org/I4210145184"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111336397","display_name":"Shao-Yuan Lo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145184","display_name":"Honda (United States)","ror":"https://ror.org/04vdmc602","country_code":"US","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210145184"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shao-Yuan Lo","raw_affiliation_strings":["Honda Research Institute,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute,USA","institution_ids":["https://openalex.org/I4210145184"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020532194","display_name":"Kwonjoon Lee","orcid":"https://orcid.org/0000-0002-1433-551X"},"institutions":[{"id":"https://openalex.org/I4210145184","display_name":"Honda (United States)","ror":"https://ror.org/04vdmc602","country_code":"US","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210145184"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwonjoon Lee","raw_affiliation_strings":["Honda Research Institute,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute,USA","institution_ids":["https://openalex.org/I4210145184"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076346273","display_name":"Qiang Ji","orcid":"https://orcid.org/0000-0002-4302-2889"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Ji","raw_affiliation_strings":["Rensselaer Polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9306,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.93701606,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"18644","last_page":"18654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9369000196456909,"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":0.9369000196456909,"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":0.9351000189781189,"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/decoupling","display_name":"Decoupling (probability)","score":0.6989926099777222},{"id":"https://openalex.org/keywords/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.6360169649124146},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5774376392364502},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5284300446510315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49766138195991516},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4296822249889374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24346444010734558},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.23934638500213623},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.1684030294418335},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1563396155834198},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12291222810745239},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10116836428642273}],"concepts":[{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.6989926099777222},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.6360169649124146},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5774376392364502},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5284300446510315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49766138195991516},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4296822249889374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24346444010734558},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.23934638500213623},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.1684030294418335},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1563396155834198},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12291222810745239},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10116836428642273},{"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/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.01764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2816413708","display_name":"EAGER: Deep Causal Representation Learning for Generalizable Visual Understanding","funder_award_id":"2236026","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309500","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2150761772","https://openalex.org/W4213201576","https://openalex.org/W1579870145","https://openalex.org/W4285549518","https://openalex.org/W2765459612","https://openalex.org/W2952741422","https://openalex.org/W3033133102","https://openalex.org/W4225846781","https://openalex.org/W2321705977","https://openalex.org/W2885024018"],"abstract_inverted_index":{"Human":[0],"action":[1,28,36,45,70,162,176],"anticipation":[2,46,71,177],"aims":[3],"at":[4],"predicting":[5],"what":[6],"people":[7],"will":[8],"do":[9],"in":[10,37,112],"the":[11,44,59,69,95,100,104,110,118,131,135,148,160,166],"future":[12],"based":[13,154],"on":[14,155,175],"past":[15],"observations.":[16],"In":[17,128],"this":[18,129],"paper,":[19],"we":[20,42,74],"introduce":[21],"Uncertainty-aware":[22],"Action":[23],"Decoupling":[24],"Transformer":[25],"(UADT)":[26],"for":[27],"anticipation.":[29,163],"Unlike":[30],"existing":[31],"methods":[32],"that":[33],"directly":[34],"predict":[35],"a":[38,76,84,88,113],"verb-noun":[39],"pair":[40],"format,":[41],"decouple":[43],"task":[47,124],"into":[48],"verb":[49,96,140,143],"and":[50,66,87,103,116,138,142,183],"noun":[51,101,132],"anticipations":[52],"separately.":[53],"The":[54,91],"objective":[55],"is":[56,81],"to":[57,98,125,158],"make":[58,159],"two":[60,149],"decoupled":[61,123],"tasks":[62],"assist":[63],"each":[64,122],"other":[65,105],"eventually":[67],"im-prove":[68],"task.":[72],"Specifically,":[73],"propose":[75],"two-stream":[77],"Transformer-based":[78],"architecture":[79],"which":[80],"composed":[82],"of":[83,121,168],"verb-to-noun":[85,92],"model":[86,93,111],"noun-to-verb":[89],"model.":[90],"leverages":[94,134],"information":[97],"improve":[99],"prediction":[102,133],"way":[106],"around.":[107],"We":[108,164],"extend":[109],"probabilistic":[114],"manner":[115],"quantify":[117],"predictive":[119],"uncertainty":[120],"select":[126],"features.":[127],"way,":[130],"most":[136],"in-formative":[137],"redundancy-free":[139],"features":[141],"pre-diction":[144],"works":[145],"similarly.":[146],"Finally,":[147],"streams":[150],"are":[151],"combined":[152],"dynamically":[153],"their":[156],"uncertainties":[157],"joint":[161],"demonstrate":[165],"efficacy":[167],"our":[169],"method":[170],"by":[171],"achieving":[172],"state-of-the-art":[173],"performance":[174],"benchmarks":[178],"including":[179],"EPIC-KITCHENS,":[180],"EGTEA":[181],"Gaze+,":[182],"50-Salads.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}