{"id":"https://openalex.org/W4392489902","doi":"https://doi.org/10.48550/arxiv.2403.02308","title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","display_name":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","publication_year":2024,"publication_date":"2024-03-04","ids":{"openalex":"https://openalex.org/W4392489902","doi":"https://doi.org/10.48550/arxiv.2403.02308"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.02308","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.02308","pdf_url":"https://arxiv.org/pdf/2403.02308","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.02308","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077749222","display_name":"Yuchen Duan","orcid":"https://orcid.org/0009-0005-5838-2253"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Duan, Yuchen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049445264","display_name":"Wei\u2010Yun Wang","orcid":"https://orcid.org/0000-0002-9783-3302"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Weiyun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457637","display_name":"Zhe Chen","orcid":"https://orcid.org/0000-0001-5004-8975"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112877229","display_name":"Xizhou Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xizhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000474748","display_name":"Lewei Lu","orcid":"https://orcid.org/0009-0009-9809-3818"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Lewei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061696740","display_name":"Tong L\u00fc","orcid":"https://orcid.org/0000-0002-7051-5347"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Tong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100732450","display_name":"Hongsheng Li","orcid":"https://orcid.org/0000-0002-2664-7975"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hongsheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026944066","display_name":"Jifeng Dai","orcid":"https://orcid.org/0000-0002-6785-0785"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Jifeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5062687402","display_name":"Wenhai Wang","orcid":"https://orcid.org/0000-0003-3707-6546"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenhai","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5077749222"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9990000128746033,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9941999912261963,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6536415815353394},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5948156118392944},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.538316547870636},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4314284026622772},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4122403562068939},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.39498287439346313},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3559519648551941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3502112925052643},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3332442343235016},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08146423101425171}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6536415815353394},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5948156118392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.538316547870636},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4314284026622772},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4122403562068939},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.39498287439346313},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3559519648551941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3502112925052643},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3332442343235016},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08146423101425171},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.02308","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.02308","pdf_url":"https://arxiv.org/pdf/2403.02308","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.2403.02308","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.02308","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.02308","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.02308","pdf_url":"https://arxiv.org/pdf/2403.02308","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":[{"id":"https://openalex.org/G4092911450","display_name":null,"funder_award_id":"62376134","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5797785011","display_name":null,"funder_award_id":"16010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392489902.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2087303720"],"abstract_inverted_index":{"Transformers":[0],"have":[1],"revolutionized":[2],"computer":[3],"vision":[4,45],"and":[5,21,62,77,117,122],"natural":[6],"language":[7],"processing,":[8],"but":[9],"their":[10,15],"high":[11],"computational":[12],"complexity":[13],"limits":[14],"application":[16],"in":[17,37,84,114],"high-resolution":[18,97,127],"image":[19,115],"processing":[20,66,96,126],"long-context":[22],"analysis.":[23],"This":[24],"paper":[25],"introduces":[26],"Vision-RWKV":[27],"(VRWKV),":[28],"a":[29,146],"model":[30,35,54],"adapted":[31],"from":[32],"the":[33,38,49,101],"RWKV":[34],"used":[36],"NLP":[39],"field":[40],"with":[41],"necessary":[42],"modifications":[43],"for":[44,103,150],"tasks.":[46,153],"Similar":[47],"to":[48,57],"Vision":[50],"Transformer":[51],"(ViT),":[52],"our":[53],"is":[55,155],"designed":[56],"efficiently":[58],"handle":[59],"sparse":[60],"inputs":[61],"demonstrate":[63,108],"robust":[64],"global":[65],"capabilities,":[67],"while":[68],"also":[69],"scaling":[70],"up":[71],"effectively,":[72],"accommodating":[73],"both":[74],"large-scale":[75],"parameters":[76],"extensive":[78],"datasets.":[79],"Its":[80],"distinctive":[81],"advantage":[82],"lies":[83],"its":[85],"reduced":[86],"spatial":[87],"aggregation":[88],"complexity,":[89],"which":[90],"renders":[91],"it":[92,133],"exceptionally":[93],"adept":[94],"at":[95,157],"images":[98],"seamlessly,":[99],"eliminating":[100],"necessity":[102],"windowing":[104],"operations.":[105],"Our":[106],"evaluations":[107],"that":[109],"VRWKV":[110],"surpasses":[111],"ViT's":[112],"performance":[113],"classification":[116],"has":[118],"significantly":[119],"faster":[120],"speeds":[121],"lower":[123],"memory":[124],"usage":[125],"inputs.":[128],"In":[129],"dense":[130],"prediction":[131],"tasks,":[132],"outperforms":[134],"window-based":[135],"models,":[136],"maintaining":[137],"comparable":[138],"speeds.":[139],"These":[140],"results":[141],"highlight":[142],"VRWKV's":[143],"potential":[144],"as":[145],"more":[147],"efficient":[148],"alternative":[149],"visual":[151],"perception":[152],"Code":[154],"released":[156],"https://github.com/OpenGVLab/Vision-RWKV.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}