{"id":"https://openalex.org/W4415980589","doi":"https://doi.org/10.1109/iccv51701.2025.01987","title":"LV-MAE: Learning Long Video Representations Through Masked-Embedding Autoencoders","display_name":"LV-MAE: Learning Long Video Representations Through Masked-Embedding Autoencoders","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415980589","doi":"https://doi.org/10.1109/iccv51701.2025.01987"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.03501","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003433915","display_name":"Ilan Naiman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ilan Naiman","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018501958","display_name":"Emanuel Ben-Baruch","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanuel Ben-Baruch","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024638180","display_name":"Oron Anschel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oron Anschel","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064987689","display_name":"Alon Shoshan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alon Shoshan","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040459833","display_name":"Igor Kviatkovsky","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Igor Kviatkovsky","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004752542","display_name":"Manoj Aggarwal","orcid":"https://orcid.org/0000-0001-5907-1995"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Manoj Aggarwal","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006918685","display_name":"G\u00e9rard Medioni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"G\u00e9rard Medioni","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":0.8063,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77876671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"21398","last_page":"21407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.43860000371932983,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.43860000371932983,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.26910001039505005,"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":0.11599999666213989,"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/autoencoder","display_name":"Autoencoder","score":0.7476999759674072},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7261000275611877},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6241999864578247},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3882000148296356},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.38440001010894775},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3529999852180481},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.3474999964237213},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.34220001101493835},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.34040001034736633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041999936103821},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7476999759674072},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7261000275611877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.671500027179718},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6241999864578247},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42829999327659607},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.38440001010894775},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3149000108242035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3052999973297119},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.3009999990463257},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2558000087738037}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.03501","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.03501","pdf_url":"https://arxiv.org/pdf/2504.03501","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},{"id":"doi:10.48550/arxiv.2504.03501","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.03501","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.03501","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.03501","pdf_url":"https://arxiv.org/pdf/2504.03501","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,59,139,175],"introduce":[4],"long-video":[5,145],"masked-embedding":[6,79],"autoencoders":[7],"(LV-MAE),":[8],"a":[9,32,78,155],"self-supervised":[10,123],"learning":[11],"framework":[12],"for":[13,31,159],"long":[14,73,126],"video":[15,35,54,127,132,183],"representation.":[16],"Our":[17],"approach":[18,121],"treats":[19],"short-":[20],"and":[21,44,92,150,170],"long-span":[22],"dependencies":[23,51],"as":[24],"two":[25],"separate":[26],"tasks.":[27],"Such":[28],"decoupling":[29],"allows":[30],"more":[33],"intuitive":[34],"processing":[36,95],"where":[37],"short-span":[38],"spatiotemporal":[39],"primitives":[40],"are":[41,45],"first":[42],"encoded":[43],"then":[46],"used":[47],"to":[48,65,90,166,185],"capture":[49],"long-range":[50],"across":[52,84],"consecutive":[53],"segments.":[55,85],"To":[56],"achieve":[57,140],"this,":[58],"leverage":[60,176],"advanced":[61],"off-the-shelf":[62],"multimodal":[63],"encoders":[64],"extract":[66],"representations":[67,184],"from":[68],"short":[69,182],"segments":[70],"within":[71],"the":[72,94,102,105,177],"video,":[74],"followed":[75],"by":[76,100],"pre-training":[77,124,169],"autoencoder":[80],"capturing":[81],"high-level":[82],"interactions":[83],"LV-MAE":[86,137,168,187],"is":[87,192],"highly":[88],"efficient":[89],"train":[91],"enables":[93],"of":[96,107,181],"much":[97],"longer":[98],"videos":[99],"alleviating":[101],"constraint":[103],"on":[104,117,143],"number":[106],"input":[108],"frames.":[109],"Furthermore,":[110],"unlike":[111],"existing":[112],"methods":[113],"that":[114],"typically":[115],"pre-train":[116],"short-video":[118],"datasets,":[119],"our":[120],"offers":[122],"using":[125],"samples":[128],"(e.g.,":[129],"20+":[130],"minutes":[131],"clips)":[133],"at":[134,194],"scale.":[135],"Using":[136],"representations,":[138],"state-of-the-art":[141],"results":[142],"three":[144],"benchmarks":[146],"--":[147,152],"LVU,":[148],"COIN,":[149],"Breakfast":[151],"employing":[153],"only":[154],"simple":[156],"classification":[157],"head":[158],"either":[160],"attentive":[161],"or":[162],"linear":[163],"probing.":[164],"Finally,":[165],"assess":[167],"visualize":[171],"its":[172],"reconstruction":[173],"quality,":[174],"video-language":[178],"aligned":[179],"space":[180],"monitor":[186],"through":[188],"video-text":[189],"retrieval.":[190],"Code":[191],"available":[193],"https://github.com/amazon-science/lv-mae.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}