{"id":"https://openalex.org/W3146947661","doi":"https://doi.org/10.1109/tcsvt.2021.3070688","title":"FactorNet: Holistic Actor, Object, and Scene Factorization for Action Recognition in Videos","display_name":"FactorNet: Holistic Actor, Object, and Scene Factorization for Action Recognition in Videos","publication_year":2021,"publication_date":"2021-04-02","ids":{"openalex":"https://openalex.org/W3146947661","doi":"https://doi.org/10.1109/tcsvt.2021.3070688","mag":"3146947661"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2021.3070688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3070688","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5021223875","display_name":"Nitika Nigam","orcid":"https://orcid.org/0000-0001-7389-6168"},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289","https://openalex.org/I91357014"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nitika Nigam","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, India"],"raw_orcid":"https://orcid.org/0000-0001-7389-6168","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088215863","display_name":"Tanima Dutta","orcid":"https://orcid.org/0000-0002-2801-0687"},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289","https://openalex.org/I91357014"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanima Dutta","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, India"],"raw_orcid":"https://orcid.org/0000-0002-2801-0687","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090813241","display_name":"Hari Prabhat Gupta","orcid":"https://orcid.org/0000-0003-3207-1340"},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289","https://openalex.org/I91357014"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hari Prabhat Gupta","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, India"],"raw_orcid":"https://orcid.org/0000-0003-3207-1340","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9703,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.76966501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"3","first_page":"976","last_page":"991"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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":0.998199999332428,"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":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.7703787088394165},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6481714844703674},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6402179002761841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6382178068161011},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6217759847640991},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5797164440155029},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5796414017677307},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4868256449699402},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.43288707733154297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703787088394165},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6481714844703674},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6402179002761841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6382178068161011},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6217759847640991},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5797164440155029},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5796414017677307},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4868256449699402},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.43288707733154297},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2021.3070688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3070688","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1485009520","https://openalex.org/W1522734439","https://openalex.org/W1578985305","https://openalex.org/W1923404803","https://openalex.org/W1927052826","https://openalex.org/W2016053056","https://openalex.org/W2099614498","https://openalex.org/W2122710056","https://openalex.org/W2126579184","https://openalex.org/W2142694332","https://openalex.org/W2235034809","https://openalex.org/W2601564443","https://openalex.org/W2619947201","https://openalex.org/W2625366777","https://openalex.org/W2732026016","https://openalex.org/W2745519816","https://openalex.org/W2798472916","https://openalex.org/W2799176631","https://openalex.org/W2806331055","https://openalex.org/W2809562466","https://openalex.org/W2883429621","https://openalex.org/W2888096830","https://openalex.org/W2895340898","https://openalex.org/W2947084868","https://openalex.org/W2962899219","https://openalex.org/W2963091558","https://openalex.org/W2963097937","https://openalex.org/W2963155035","https://openalex.org/W2963246338","https://openalex.org/W2963457877","https://openalex.org/W2963524571","https://openalex.org/W2963645879","https://openalex.org/W2963722382","https://openalex.org/W2963820951","https://openalex.org/W2964191259","https://openalex.org/W2967918518","https://openalex.org/W2981385151","https://openalex.org/W2983465317","https://openalex.org/W2984287396","https://openalex.org/W2990503944","https://openalex.org/W2997582214","https://openalex.org/W3006771725","https://openalex.org/W3014447010","https://openalex.org/W3104962140","https://openalex.org/W4287825490","https://openalex.org/W6600983433","https://openalex.org/W6630875275","https://openalex.org/W6638667902","https://openalex.org/W6682864246","https://openalex.org/W6742667445","https://openalex.org/W6743837088","https://openalex.org/W6757040593","https://openalex.org/W6774701426","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2020516640","https://openalex.org/W4320197069","https://openalex.org/W3123139907","https://openalex.org/W2200925278","https://openalex.org/W2005530432","https://openalex.org/W2104777652","https://openalex.org/W2613077666","https://openalex.org/W2141093233","https://openalex.org/W2162428484","https://openalex.org/W1989819216"],"abstract_inverted_index":{"The":[0,182],"ability":[1],"to":[2,12,88,99,160,189],"recognize":[3],"human":[4,23,47,62,74],"actions":[5,48,75,210],"in":[6,35,102,121,213],"a":[7,106,151,169,196],"video":[8,17],"is":[9],"challenging":[10],"due":[11],"the":[13,20,69,77,81,90,100,137,162],"complex":[14],"nature":[15],"of":[16,22,45,71,73,92,154,164,207],"data":[18],"and":[19,33,55,85,140,178],"subtlety":[21],"actions.":[24,63],"Human":[25],"activities":[26],"often":[27,59],"get":[28],"associated":[29,138],"with":[30,123],"surrounding":[31],"objects":[32,54,139],"occur":[34,212],"specific":[36],"scene":[37,142],"contexts.":[38],"Existing":[39],"action":[40,101,119,174,191],"recognition":[41,120],"systems":[42],"are":[43,97],"incapable":[44],"separating":[46],"from":[49,136],"representation":[50,93,184],"biases,":[51],"like":[52],"co-occurring":[53,83,141],"underlying":[56,86],"scene,":[57],"which":[58,205],"dominate":[60],"subtle":[61],"In":[64],"this":[65],"paper,":[66],"we":[67],"address":[68],"issue":[70],"factorization":[72],"into":[76],"activity":[78],"performed":[79],"by":[80,112,144],"actor,":[82],"objects,":[84],"context":[87],"mitigate":[89],"influence":[91],"biases":[94],"when":[95],"they":[96],"irrelevant":[98],"consideration.":[103],"We":[104,127,149,193],"propose":[105],"deep":[107],"neural":[108],"network":[109],"architecture,":[110],"denoted":[111],"<italic":[113,201],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[114,202],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">FactorNet</i>":[115],",":[116,204],"for":[117],"efficient":[118],"videos":[122],"long":[124],"temporal":[125,147],"duration.":[126],"design":[128,195],"an":[129,134],"attention":[130],"mechanism":[131],"that":[132,211],"separates":[133],"actor":[135],"followed":[143],"capturing":[145],"long-range":[146],"context.":[148],"perform":[150],"comprehensive":[152],"set":[153],"experimentation":[155],"on":[156],"six":[157],"benchmark":[158],"datasets":[159,175],"show":[161],"efficacy":[163],"our":[165],"architecture.":[166],"To":[167],"train":[168],"model":[170],"using":[171],"recent":[172],"video-based":[173],"certainly":[176],"capture":[177],"leverages":[179],"such":[180],"bias.":[181],"supervised":[183],"may":[185],"not":[186],"be":[187],"competent":[188],"new":[190,197],"classes.":[192],"therefore":[194],"dataset,":[198],"known":[199],"as":[200],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">FactNet</i>":[203],"consists":[206],"activity-object-scene":[208],"related":[209],"day-to-day":[214],"applications.":[215],"Dataset":[216],"Link:":[217],"FactNet.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}