{"id":"https://openalex.org/W4404569698","doi":"https://doi.org/10.1109/iccv51701.2025.01981","title":"Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation","display_name":"Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404569698","doi":"https://doi.org/10.1109/iccv51701.2025.01981"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01981","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/2411.10281","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050136744","display_name":"Tim Elsner","orcid":"https://orcid.org/0000-0003-1309-8003"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tim Elsner","raw_affiliation_strings":["RWTH Aachen University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114730039","display_name":"Paula Usinger","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Paula Usinger","raw_affiliation_strings":["RWTH Aachen University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006690519","display_name":"Julius Nehring-Wirxel","orcid":"https://orcid.org/0000-0003-2194-2227"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julius Nehring-Wirxel","raw_affiliation_strings":["RWTH Aachen University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044399422","display_name":"Gregor Kobsik","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gregor Kobsik","raw_affiliation_strings":["RWTH Aachen University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047205609","display_name":"Victor Czech","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Victor Czech","raw_affiliation_strings":["RWTH Aachen University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045331954","display_name":"Yan\u2010Lin He","orcid":"https://orcid.org/0000-0001-9999-3679"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yanjiang He","raw_affiliation_strings":["RWTH Aachen University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028411232","display_name":"Isaak Lim","orcid":"https://orcid.org/0000-0002-8160-2315"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Isaak Lim","raw_affiliation_strings":["RWTH Aachen University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036300670","display_name":"Leif Kobbelt","orcid":"https://orcid.org/0000-0002-7880-9470"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leif Kobbelt","raw_affiliation_strings":["RWTH Aachen University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5050136744"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00169189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21331","last_page":"21341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12698","display_name":"3D Modeling in Geospatial Applications","score":0.8909000158309937,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12698","display_name":"3D Modeling in Geospatial Applications","score":0.8909000158309937,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.8773999810218811,"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"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.8190000057220459,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.8061308860778809},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7042781114578247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6291428804397583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29449689388275146},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1275431513786316}],"concepts":[{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.8061308860778809},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7042781114578247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6291428804397583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29449689388275146},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1275431513786316}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01981","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:2411.10281","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.10281","pdf_url":"https://arxiv.org/pdf/2411.10281","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.10281","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.10281","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.10281","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.10281","pdf_url":"https://arxiv.org/pdf/2411.10281","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404569698.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3042604642","https://openalex.org/W121858127","https://openalex.org/W2775143306","https://openalex.org/W2390279801","https://openalex.org/W4289329995","https://openalex.org/W2373574911","https://openalex.org/W2046727832"],"abstract_inverted_index":{"In":[0,33],"language":[1],"processing,":[2],"transformers":[3,144],"benefit":[4],"greatly":[5],"from":[6,49,68],"text":[7],"being":[8],"condensed.":[9],"This":[10,25,129],"is":[11,26,42,130],"achieved":[12,148],"through":[13,83],"a":[14,74,97,109,131,190],"larger":[15],"vocabulary":[16],"that":[17],"captures":[18],"word":[19],"fragments":[20],"instead":[21],"of":[22,36,39,60,86,111,143,153],"plain":[23],"characters.":[24],"often":[27],"done":[28],"with":[29,96,160],"Byte":[30,65],"Pair":[31,66],"Encoding.":[32],"the":[34,91,105,199],"context":[35],"images,":[37,114],"tokenisation":[38,59],"visual":[40,61,146],"data":[41,62,147],"usually":[43],"limited":[44],"to":[45,70,77,119,185,192],"regular":[46],"grids":[47],"obtained":[48],"quantisation":[50],"methods,":[51],"without":[52],"global":[53],"content":[54],"awareness.":[55],"Our":[56,135],"work":[57],"improves":[58],"by":[63,108,149,197],"bringing":[64],"Encoding":[67],"1D":[69],"multiple":[71],"dimensions,":[72],"as":[73],"complementary":[75],"add-on":[76],"existing":[78],"compression.":[79],"We":[80,187],"achieve":[81],"this":[82,194],"counting":[84],"constellations":[85,152],"token":[87,94],"pairs":[88],"and":[89,140],"replacing":[90],"most":[92],"frequent":[93,151],"pair":[95],"newly":[98],"introduced":[99],"token.":[100],"The":[101,155],"multidimensionality":[102],"only":[103],"increases":[104],"computation":[106],"time":[107],"factor":[110],"2":[112],"for":[113],"making":[115],"it":[116],"applicable":[117],"even":[118],"large":[120],"datasets":[121],"like":[122],"ImageNet":[123],"within":[124],"minutes":[125],"on":[126,145],"consumer":[127],"hardware.":[128],"lossless":[132],"preprocessing":[133],"step.":[134],"evaluation":[136],"shows":[137],"improved":[138],"training":[139],"inference":[141],"performance":[142],"compressing":[150],"tokens:":[154],"resulting":[156],"sequences":[157,182],"are":[158,183],"shorter,":[159],"more":[161],"uniformly":[162],"distributed":[163],"information":[164],"content,":[165],"e.g.":[166],"condensing":[167],"empty":[168],"regions":[169],"in":[170],"an":[171],"image":[172],"into":[173],"single":[174],"tokens.":[175],"As":[176],"our":[177],"experiments":[178],"show,":[179],"these":[180],"condensed":[181],"easier":[184],"process.":[186],"additionally":[188],"introduce":[189],"strategy":[191],"amplify":[193],"compression":[195],"further":[196],"clustering":[198],"vocabulary.":[200]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2024-11-21T00:00:00"}