{"id":"https://openalex.org/W3106884574","doi":"https://doi.org/10.1109/tip.2020.3040521","title":"Learning to Anticipate Egocentric Actions by Imagination","display_name":"Learning to Anticipate Egocentric Actions by Imagination","publication_year":2020,"publication_date":"2020-12-03","ids":{"openalex":"https://openalex.org/W3106884574","doi":"https://doi.org/10.1109/tip.2020.3040521","mag":"3106884574","pmid":"https://pubmed.ncbi.nlm.nih.gov/33270562"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2020.3040521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3040521","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.04924","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-1680-8253"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1680-8253","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Linchao Zhu","orcid":"https://orcid.org/0000-0002-4093-7557"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Linchao Zhu","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4093-7557","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaohan Wang","orcid":"https://orcid.org/0000-0001-6206-7911"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaohan Wang","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6206-7911","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0512-880X","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":null,"display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2139-8807","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6541,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.94107616,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"1143","last_page":"1152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.49540001153945923,"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":0.49540001153945923,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.08489999920129776,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0681999996304512,"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/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.8439000248908997},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6905999779701233},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5817999839782715},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.578499972820282},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5209000110626221},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.48500001430511475},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.43779999017715454},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4120999872684479}],"concepts":[{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.8439000248908997},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6905999779701233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6628999710083008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6353999972343445},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5817999839782715},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5209000110626221},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3917999863624573},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33559998869895935},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2847999930381775},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C2780667275","wikidata":"https://www.wikidata.org/wiki/Q39640","display_name":"Setter","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2020.3040521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3040521","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:33270562","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33270562","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:arXiv.org:2101.04924","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.04924","pdf_url":"https://arxiv.org/pdf/2101.04924","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.04924","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.04924","pdf_url":"https://arxiv.org/pdf/2101.04924","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1483019628","https://openalex.org/W1522734439","https://openalex.org/W2064675550","https://openalex.org/W2260280755","https://openalex.org/W2342437993","https://openalex.org/W2422305492","https://openalex.org/W2472970127","https://openalex.org/W2507009361","https://openalex.org/W2524365899","https://openalex.org/W2559542432","https://openalex.org/W2605300166","https://openalex.org/W2763331099","https://openalex.org/W2777985721","https://openalex.org/W2779943048","https://openalex.org/W2780253814","https://openalex.org/W2798991696","https://openalex.org/W2799352756","https://openalex.org/W2800438594","https://openalex.org/W2842511635","https://openalex.org/W2894666173","https://openalex.org/W2895189911","https://openalex.org/W2895299763","https://openalex.org/W2897187502","https://openalex.org/W2909398625","https://openalex.org/W2948971113","https://openalex.org/W2951870359","https://openalex.org/W2960747818","https://openalex.org/W2963082988","https://openalex.org/W2963302737","https://openalex.org/W2963482775","https://openalex.org/W2963570630","https://openalex.org/W2963610939","https://openalex.org/W2963692464","https://openalex.org/W2963720581","https://openalex.org/W2971486392","https://openalex.org/W2971680695","https://openalex.org/W2989839235","https://openalex.org/W2993447238","https://openalex.org/W2995301359","https://openalex.org/W3020843970","https://openalex.org/W3035524453","https://openalex.org/W3048602385","https://openalex.org/W3096383329","https://openalex.org/W3109652723","https://openalex.org/W6638667902","https://openalex.org/W6682864246","https://openalex.org/W6682948231","https://openalex.org/W6736809608","https://openalex.org/W6749916090","https://openalex.org/W6753596515","https://openalex.org/W6753924131","https://openalex.org/W6756040250","https://openalex.org/W6757613341","https://openalex.org/W6758736441","https://openalex.org/W6772408192","https://openalex.org/W6774314701","https://openalex.org/W6779499151","https://openalex.org/W6781471103"],"related_works":[],"abstract_inverted_index":{"Anticipating":[0],"actions":[1],"before":[2,35],"they":[3],"are":[4],"executed":[5],"is":[6,37,123,195],"crucial":[7],"for":[8,39,75,198],"a":[9,92,126,136],"wide":[10],"range":[11],"of":[12,79,94,131,167,171,213,233],"practical":[13],"applications,":[14],"including":[15],"autonomous":[16],"driving":[17],"and":[18,50,109,228],"robotics.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23,68],"study":[24],"the":[25,47,64,76,80,88,101,106,141,145,164,172,177,185,189,200,211,224,229,234],"egocentric":[26,40,207],"action":[27,33,54,65,89,113,208],"anticipation":[28,66,90],"task,":[29],"which":[30],"predicts":[31,111],"future":[32,53,95,108,112,147,186],"seconds":[34],"it":[36,61],"performed":[38],"videos.":[41],"Previous":[42],"approaches":[43],"focus":[44,180],"on":[45,56,116,181,204,222],"summarizing":[46],"observed":[48],"content":[49],"directly":[51],"predicting":[52,163],"based":[55,115],"past":[57],"observations.":[58],"We":[59,83,98,134,151],"believe":[60],"would":[62],"benefit":[63],"if":[67],"could":[69],"mine":[70],"some":[71],"cues":[72],"to":[73,86,139,162,179],"compensate":[74],"missing":[77],"information":[78],"unobserved":[81],"frames.":[82],"then":[84,110],"propose":[85],"decompose":[87],"into":[91],"series":[93],"feature":[96,103,132,165],"predictions.":[97],"imagine":[99],"how":[100],"visual":[102],"changes":[104],"in":[105,125],"near":[107],"labels":[114],"these":[117],"imagined":[118],"representations.":[119],"Differently,":[120],"our":[121,182,214],"ImagineRNN":[122,154],"optimized":[124],"contrastive":[127],"learning":[128],"way":[129],"instead":[130,170],"regression.":[133],"utilize":[135],"proxy":[137],"task":[138],"train":[140],"ImagineRNN,":[142],"i.e.,":[143,158,184],"selecting":[144],"correct":[146],"states":[148],"from":[149],"distractors.":[150],"further":[152],"improve":[153],"by":[155],"residual":[156],"anticipation,":[157],"changing":[159],"its":[160],"target":[161],"difference":[166,190],"adjacent":[168,192],"frames":[169],"frame":[173,193],"content.":[174],"This":[175],"promotes":[176],"network":[178],"target,":[183],"action,":[187],"as":[188],"between":[191],"features":[194],"more":[196],"important":[197],"forecasting":[199],"future.":[201],"Extensive":[202],"experiments":[203],"two":[205],"large-scale":[206],"datasets":[209],"validate":[210],"effectiveness":[212],"method.":[215],"Our":[216],"method":[217],"significantly":[218],"outperforms":[219],"previous":[220],"methods":[221],"both":[223],"seen":[225],"test":[226,231],"set":[227,232],"unseen":[230],"EPIC":[235],"Kitchens":[236],"Action":[237],"Anticipation":[238],"Challenge.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":11}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2020-12-07T00:00:00"}