{"id":"https://openalex.org/W4417285899","doi":"https://doi.org/10.1109/iccv51701.2025.01969","title":"VAMBA: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","display_name":"VAMBA: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417285899","doi":"https://doi.org/10.1109/iccv51701.2025.01969"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01969","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.11579","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039017989","display_name":"Weiming Ren","orcid":"https://orcid.org/0000-0001-7824-6404"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Weiming Ren","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031638251","display_name":"Wentao Ma","orcid":"https://orcid.org/0000-0003-3059-6629"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wentao Ma","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002790571","display_name":"Huan Yang","orcid":"https://orcid.org/0000-0002-4595-9878"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Huan Yang","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cong Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cong Wei","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326077","display_name":"Ge Zhang","orcid":"https://orcid.org/0000-0003-0704-0657"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ge Zhang","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103103242","display_name":"Wenhu Chen","orcid":"https://orcid.org/0000-0002-8609-7821"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wenhu Chen","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21197","last_page":"21208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3028999865055084,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3028999865055084,"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":0.2962000072002411,"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":0.14839999377727509,"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/encode","display_name":"ENCODE","score":0.8779000043869019},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7224000096321106},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.578499972820282},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5396000146865845},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4415000081062317},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.3896999955177307},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.35830000042915344},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.3490999937057495}],"concepts":[{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.8779000043869019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883999943733215},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7224000096321106},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48590001463890076},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3668999969959259},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36320000886917114},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.35830000042915344},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.2906999886035919},{"id":"https://openalex.org/C104759252","wikidata":"https://www.wikidata.org/wiki/Q187120","display_name":"Time shifting","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2563999891281128}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01969","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:2503.11579","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11579","pdf_url":"https://arxiv.org/pdf/2503.11579","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.11579","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.11579","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.11579","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11579","pdf_url":"https://arxiv.org/pdf/2503.11579","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":"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"State-of-the-art":[0],"transformer-based":[1,96,131],"large":[2],"multimodal":[3],"models":[4,97],"(LMMs)":[5],"struggle":[6],"to":[7,13,23,61,72,130],"handle":[8],"hour-long":[9,146],"video":[10,39,74,105,147,154,168],"inputs":[11],"due":[12],"the":[14,18,36,124,144],"quadratic":[15],"complexity":[16],"of":[17,38,164],"causal":[19],"self-attention":[20],"operations,":[21],"leading":[22],"high":[24],"computational":[25],"costs":[26],"during":[27,117],"training":[28,118,127],"and":[29,46,119,121,156,166],"inference.":[30],"Existing":[31],"token":[32,81],"compression-based":[33],"methods":[34],"reduce":[35],"number":[37],"tokens":[40,75],"but":[41],"often":[42],"incur":[43],"information":[44],"loss":[45],"remain":[47],"inefficient":[48],"for":[49],"extremely":[50],"long":[51,104,165],"sequences.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"explore":[57],"an":[58],"orthogonal":[59],"direction":[60],"build":[62],"a":[63,92,161],"hybrid":[64],"Mamba-Transformer":[65],"model":[66],"(VAMBA)":[67],"that":[68,137],"employs":[69],"Mamba-2":[70],"blocks":[71],"encode":[73,85,100],"with":[76],"linear":[77],"complexity.":[78],"Without":[79],"any":[80],"reduction,":[82],"VAMBA":[83,107,138],"can":[84,98],"more":[86],"than":[87],"1024":[88],"frames":[89],"(640$\\times$360)":[90],"on":[91,143,160],"single":[93],"GPU,":[94],"while":[95],"only":[99],"256":[101],"frames.":[102],"On":[103],"input,":[106],"achieves":[108],"at":[109],"least":[110],"50%":[111],"reduction":[112],"in":[113],"GPU":[114],"memory":[115],"usage":[116],"inference,":[120],"nearly":[122],"doubles":[123],"speed":[125],"per":[126],"step":[128],"compared":[129],"LMMs.":[132],"Our":[133],"experimental":[134],"results":[135],"demonstrate":[136],"improves":[139],"accuracy":[140],"by":[141],"4.3%":[142],"challenging":[145],"understanding":[148,169],"benchmark":[149],"LVBench":[150],"over":[151],"prior":[152],"efficient":[153],"LMMs,":[155],"maintains":[157],"strong":[158],"performance":[159],"broad":[162],"spectrum":[163],"short":[167],"tasks.":[170]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}