{"id":"https://openalex.org/W4411244563","doi":"https://doi.org/10.5244/c.35.71","title":"MVT: Multi-view Vision Transformer for 3D Object Recognition","display_name":"MVT: Multi-view Vision Transformer for 3D Object Recognition","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W4411244563","doi":"https://doi.org/10.5244/c.35.71"},"language":"en","primary_location":{"id":"doi:10.5244/c.35.71","doi":"https://doi.org/10.5244/c.35.71","is_oa":false,"landing_page_url":"https://doi.org/10.5244/c.35.71","pdf_url":null,"source":{"id":"https://openalex.org/S7407088578","display_name":"British Machine Vision Conference (BMVC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the British Machine Vision Conference 2021","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://handle.uba.uva.nl/personal/pure/en/publications/mvt-multiview-vision-transformer-for-3d-object-recognition(e8212e26-5505-4856-8c4a-78fc014dbdc0).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115861810","display_name":"Shuo Chen","orcid":"https://orcid.org/0000-0002-0678-7380","observed_orcids":["https://orcid.org/0000-0002-0678-7380","https://orcid.org/0009-0007-6563-0037"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuo Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018887598","display_name":"Tan Yu","orcid":"https://orcid.org/0000-0001-6071-0395","observed_orcids":["https://orcid.org/0000-0001-6071-0395"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100435527","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-8515-7773","observed_orcids":["https://orcid.org/0000-0002-8515-7773","https://orcid.org/0000-0002-5979-8868","https://orcid.org/0000-0002-7985-8477","https://orcid.org/0000-0002-1503-0240","https://orcid.org/0000-0002-8391-6510","https://orcid.org/0000-0001-8285-8921","https://orcid.org/0000-0003-4725-4553"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8917,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.90584683,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.5551999807357788,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.5551999807357788,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.38109999895095825,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.04749999940395355,"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/3d-object-recognition","display_name":"3D object recognition","score":0.8930000066757202},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.718999981880188},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.7149999737739563},{"id":"https://openalex.org/keywords/modelnet40","display_name":"ModelNet40","score":0.8399999737739563},{"id":"https://openalex.org/keywords/modelnet10","display_name":"ModelNet10","score":0.9929999709129333}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7402942776679993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6990708708763123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6921733617782593},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5668492913246155},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.5195860862731934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34462931752204895},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.34400302171707153},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12052670121192932},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08260735869407654},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0653521716594696}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5244/c.35.71","doi":"https://doi.org/10.5244/c.35.71","is_oa":false,"landing_page_url":"https://doi.org/10.5244/c.35.71","pdf_url":null,"source":{"id":"https://openalex.org/S7407088578","display_name":"British Machine Vision Conference (BMVC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the British Machine Vision Conference 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/e8212e26-5505-4856-8c4a-78fc014dbdc0","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/mvt-multiview-vision-transformer-for-3d-object-recognition(e8212e26-5505-4856-8c4a-78fc014dbdc0).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Chen, S, Yu, T & Li, P 2021, MVT: Multi-view Vision Transformer for 3D object recognition. in 32nd British Machine Vision Conference 2021 : BMVC 2021, Online, November 22-25, 2021., 349, 32nd British Machine Vision Conference, United Kingdom, 22/11/21.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:2110.13083","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.13083","pdf_url":"https://arxiv.org/pdf/2110.13083","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2110.13083","doi":"https://doi.org/10.48550/arxiv.2110.13083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.13083","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire/e8212e26-5505-4856-8c4a-78fc014dbdc0","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/mvt-multiview-vision-transformer-for-3d-object-recognition(e8212e26-5505-4856-8c4a-78fc014dbdc0).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Chen, S, Yu, T & Li, P 2021, MVT: Multi-view Vision Transformer for 3D object recognition. in 32nd British Machine Vision Conference 2021 : BMVC 2021, Online, November 22-25, 2021., 349, 32nd British Machine Vision Conference, United Kingdom, 22/11/21.","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411244563.pdf","grobid_xml":"https://content.openalex.org/works/W4411244563.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2211722331","https://openalex.org/W2400418317","https://openalex.org/W2560609797","https://openalex.org/W2624503621","https://openalex.org/W2626778328","https://openalex.org/W2768213582","https://openalex.org/W2798998662","https://openalex.org/W2890018557","https://openalex.org/W2893477965","https://openalex.org/W2905564365","https://openalex.org/W2908510526","https://openalex.org/W2921891839","https://openalex.org/W2958885478","https://openalex.org/W2963341956","https://openalex.org/W2964342398","https://openalex.org/W2986519121","https://openalex.org/W3035541121","https://openalex.org/W3037932933","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3133696297","https://openalex.org/W3138516171","https://openalex.org/W3157528469","https://openalex.org/W3170974475","https://openalex.org/W3202715235","https://openalex.org/W3203606893","https://openalex.org/W3204076343","https://openalex.org/W3211432419"],"related_works":["https://openalex.org/W4385431648","https://openalex.org/W4323057853","https://openalex.org/W7168037489","https://openalex.org/W4402782556","https://openalex.org/W4396733090","https://openalex.org/W4386158774","https://openalex.org/W3115567406","https://openalex.org/W2582680369","https://openalex.org/W4214655709","https://openalex.org/W4312904243"],"abstract_inverted_index":{"Inspired":[0,48],"by":[1,6,49,54],"the":[2,17,34,50,128],"great":[3],"success":[4,52],"achieved":[5,25],"CNN":[7,30,103],"in":[8,44,57,75],"image":[9,58],"recognition,":[10,59],"view-based":[11],"methods":[12],"applied":[13],"CNNs":[14],"to":[15],"model":[16,33],"projected":[18],"views":[19],"for":[20,67,115],"3D":[21,45,68],"object":[22,46,69],"understanding":[23],"and":[24,108,125],"excellent":[26],"performance.":[27],"Nevertheless,":[28],"multi-view":[29],"models":[31],"cannot":[32],"communications":[35,87],"between":[36,88],"patches":[37,89],"from":[38,90],"different":[39,91],"views,":[40],"limiting":[41],"its":[42,102],"effectiveness":[43,107],"recognition.":[47,70],"recent":[51],"gained":[53],"vision":[55],"Transformer":[56,65,77],"we":[60,110],"propose":[61],"a":[62,76,80,112],"Multi-view":[63],"Vision":[64],"(MVT)":[66],"Since":[71],"each":[72],"patch":[73],"feature":[74],"block":[78],"has":[79],"global":[81],"reception":[82],"field,":[83],"it":[84,94],"naturally":[85],"achieves":[86],"views.":[92],"Meanwhile,":[93],"takes":[95],"much":[96],"less":[97],"inductive":[98],"bias":[99],"compared":[100],"with":[101],"counterparts.":[104],"Considering":[105],"both":[106],"efficiency,":[109],"develop":[111],"global-local":[113],"structure":[114],"our":[116,132],"MVT.":[117,133],"Our":[118],"experiments":[119],"on":[120],"two":[121],"public":[122],"benchmarks,":[123],"ModelNet40":[124],"ModelNet10,":[126],"demonstrate":[127],"competitive":[129],"performance":[130],"of":[131]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-10T00:00:00"}