{"id":"https://openalex.org/W4312931690","doi":"https://doi.org/10.1109/cvpr52688.2022.00812","title":"Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models","display_name":"Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4312931690","doi":"https://doi.org/10.1109/cvpr52688.2022.00812"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52688.2022.00812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.00812","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5101701469","display_name":"Feng Cheng","orcid":"https://orcid.org/0000-0002-0090-0805"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng Cheng","raw_affiliation_strings":["UNC Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024342916","display_name":"Mingze Xu","orcid":"https://orcid.org/0000-0003-3082-5313"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingze Xu","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005925571","display_name":"Yuanjun Xiong","orcid":"https://orcid.org/0000-0002-6391-4921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanjun Xiong","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353664","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0003-4417-614X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406079","display_name":"Xinyu Li","orcid":"https://orcid.org/0000-0001-5398-3707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Li","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317994","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-7015-7335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100654154","display_name":"Wei Xia","orcid":"https://orcid.org/0000-0003-3157-6988"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xia","raw_affiliation_strings":["AWS AI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8291","last_page":"8300"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9973999857902527,"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/backpropagation","display_name":"Backpropagation","score":0.9128040075302124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8491920232772827},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.692852258682251},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6360698938369751},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5781295299530029},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5638503432273865},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5014691352844238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4715167284011841},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.31985393166542053}],"concepts":[{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.9128040075302124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8491920232772827},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.692852258682251},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6360698938369751},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5781295299530029},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5638503432273865},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5014691352844238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4715167284011841},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.31985393166542053},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52688.2022.00812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.00812","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1927052826","https://openalex.org/W1947050545","https://openalex.org/W2156303437","https://openalex.org/W2194775991","https://openalex.org/W2336403884","https://openalex.org/W2338908902","https://openalex.org/W2342437993","https://openalex.org/W2507009361","https://openalex.org/W2593722617","https://openalex.org/W2597958930","https://openalex.org/W2619947201","https://openalex.org/W2755876276","https://openalex.org/W2955874753","https://openalex.org/W2956434358","https://openalex.org/W2962677524","https://openalex.org/W2962876901","https://openalex.org/W2962972527","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963795951","https://openalex.org/W2964008341","https://openalex.org/W2964110616","https://openalex.org/W2964216549","https://openalex.org/W2964222622","https://openalex.org/W2983918066","https://openalex.org/W2989506443","https://openalex.org/W3003341156","https://openalex.org/W3004505825","https://openalex.org/W3034623254","https://openalex.org/W3035104321","https://openalex.org/W3035130921","https://openalex.org/W3035350782","https://openalex.org/W3098366850","https://openalex.org/W3098872093","https://openalex.org/W3107666194","https://openalex.org/W3123394884","https://openalex.org/W3128626728","https://openalex.org/W3154596443","https://openalex.org/W3173392600","https://openalex.org/W3174114091","https://openalex.org/W3176444885","https://openalex.org/W3177141386","https://openalex.org/W3179107710","https://openalex.org/W3182022070","https://openalex.org/W3210279979","https://openalex.org/W3212973774","https://openalex.org/W4214516465","https://openalex.org/W4214612132","https://openalex.org/W4312560592","https://openalex.org/W6682864246","https://openalex.org/W6703652217","https://openalex.org/W6748489640","https://openalex.org/W6749916090","https://openalex.org/W6761472960","https://openalex.org/W6765532259","https://openalex.org/W6779944756","https://openalex.org/W6785095303","https://openalex.org/W6785160378","https://openalex.org/W6789619165","https://openalex.org/W6790307280","https://openalex.org/W6793736971","https://openalex.org/W6794642395","https://openalex.org/W6797737728","https://openalex.org/W6798038150","https://openalex.org/W6798533924","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2317245370","https://openalex.org/W4249323025","https://openalex.org/W198851386","https://openalex.org/W2030310580","https://openalex.org/W947442053","https://openalex.org/W1980160788","https://openalex.org/W2148915962","https://openalex.org/W2283866686","https://openalex.org/W4287182096","https://openalex.org/W27867058"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,106],"memory":[3,73,120],"efficient":[4],"method,":[5],"named":[6],"Stochastic":[7],"Backpropagation":[8],"(SBP),":[9],"for":[10,28,61,111],"training":[11,67,124],"deep":[12],"neural":[13],"networks":[14],"on":[15,20,132],"videos.":[16],"It":[17,69],"is":[18],"based":[19],"the":[21,34,43,58,71,77,85],"finding":[22],"that":[23,100],"gradients":[24],"from":[25],"incomplete":[26],"execution":[27],"backpropagation":[29],"can":[30,91,102],"still":[31],"effectively":[32],"train":[33],"models":[35,110],"with":[36,126],"minimal":[37],"accuracy":[38,130],"loss,":[39],"which":[40],"attributes":[41],"to":[42,79,84,105,115,117],"high":[44],"redundancy":[45],"of":[46,109],"video.":[47],"SBP":[48,101],"keeps":[49],"all":[50],"forward":[51],"paths":[52,60],"but":[53],"randomly":[54],"and":[55,122,135],"independently":[56],"removes":[57],"backward":[59,87],"each":[62,66],"network":[63],"layer":[64],"in":[65],"step.":[68],"reduces":[70],"GPU":[72,119],"cost":[74],"by":[75,94],"eliminating":[76],"need":[78],"cache":[80],"activation":[81],"values":[82],"corresponding":[83],"dropped":[86],"paths,":[88],"whose":[89],"amount":[90],"be":[92,103],"controlled":[93],"an":[95],"adjustable":[96],"keep-ratio.":[97],"Experiments":[98],"show":[99],"applied":[104],"wide":[107],"range":[108],"video":[112],"tasks,":[113],"leading":[114],"up":[116],"80.0%":[118],"saving":[121],"10%":[123],"speedup":[125],"less":[127],"than":[128],"1%":[129],"drop":[131],"action":[133,137],"recognition":[134],"temporal":[136],"detection.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}