{"id":"https://openalex.org/W7131433167","doi":"https://doi.org/10.1109/tpami.2026.3667935","title":"Codebook Transfer With Vision-to-Language Translation for Vector Quantization","display_name":"Codebook Transfer With Vision-to-Language Translation for Vector Quantization","publication_year":2026,"publication_date":"2026-02-25","ids":{"openalex":"https://openalex.org/W7131433167","doi":"https://doi.org/10.1109/tpami.2026.3667935","pmid":"https://pubmed.ncbi.nlm.nih.gov/41740096"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3667935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3667935","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101679400","display_name":"Baoquan Zhang","orcid":"https://orcid.org/0000-0001-6178-6797"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoquan Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6178-6797","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113395536","display_name":"Guotao Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guotao Liang","raw_affiliation_strings":["School of Computer Science and Technology, Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0007-8935-8322","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108149716","display_name":"Tianran Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianran Chen","raw_affiliation_strings":["School of Computer Science and Technology, Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126808256","display_name":"Yunming Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunming Ye","raw_affiliation_strings":["School of Computer Science and Technology, Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1807-8581","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048809651","display_name":"Zhiyuan Wen","orcid":"https://orcid.org/0000-0003-4106-1312"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Wen","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004199412","display_name":"Xiaochen Qi","orcid":"https://orcid.org/0009-0006-4081-895X"},"institutions":[{"id":"https://openalex.org/I4210089559","display_name":"Shenzhen Metro (China)","ror":"https://ror.org/008hpge95","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210089559"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochen Qi","raw_affiliation_strings":["ShenZhen SiFar Co., Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShenZhen SiFar Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210089559"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100509446","display_name":"Yao He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089559","display_name":"Shenzhen Metro (China)","ror":"https://ror.org/008hpge95","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210089559"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao He","raw_affiliation_strings":["ShenZhen SiFar Co., Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShenZhen SiFar Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210089559"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1902662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"7","first_page":"7656","last_page":"7673"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5612999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5612999796867371,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10499999672174454,"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":0.023800000548362732,"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/codebook","display_name":"Codebook","score":0.9940999746322632},{"id":"https://openalex.org/keywords/linde\u2013buzo\u2013gray-algorithm","display_name":"Linde\u2013Buzo\u2013Gray algorithm","score":0.9488999843597412},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6123999953269958},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.48489999771118164},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4691999852657318},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45500001311302185},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.398499995470047},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.3644999861717224}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.9940999746322632},{"id":"https://openalex.org/C93372532","wikidata":"https://www.wikidata.org/wiki/Q6552455","display_name":"Linde\u2013Buzo\u2013Gray algorithm","level":3,"score":0.9488999843597412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988000273704529},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6123999953269958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.609000027179718},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45500001311302185},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3644999861717224},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28929999470710754},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2888000011444092},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C153207627","wikidata":"https://www.wikidata.org/wiki/Q863873","display_name":"Code word","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26109999418258667}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3667935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3667935","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41740096","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41740096","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1686588096","display_name":null,"funder_award_id":"2025YFE0103100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2874901904","display_name":null,"funder_award_id":"62272130","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6249864047","display_name":null,"funder_award_id":"62502120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7332461653","display_name":null,"funder_award_id":"2025A1515011674","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vector":[0],"quantization":[1],"(VQ)":[2],"is":[3,58,124,195],"a":[4,18,30,37,49,55,64,111,115,134,148,165,179,190,247],"fundamental":[5],"research":[6],"problem":[7,27],"in":[8,36,54,127,205],"image":[9,16,219,238],"synthesis,":[10],"which":[11,61,144],"aims":[12,145],"to":[13,40,80,146,155,197,228,251],"represent":[14],"an":[15],"with":[17,139,182],"discrete":[19,31,45],"token":[20],"sequence.":[21],"Existing":[22],"studies":[23],"effectively":[24],"address":[25],"this":[26,95,130,234],"by":[28,98],"learning":[29,48],"codebook":[32,50,68,87,113,136,150,159,167,181,187,192,210,226,255],"from":[33,51,151,168],"scratch":[34,52],"and":[35,53,85,171,244],"code-independent":[38,56],"manner":[39,57],"quantize":[41],"continuous":[42],"representations":[43],"into":[44],"tokens.":[46],"However,":[47],"highly":[59],"challenging,":[60],"may":[62],"be":[63,76],"key":[65],"reason":[66],"causing":[67],"collapse,":[69],"i.e.,":[70],"some":[71],"code":[72],"vectors":[73],"can":[74,216],"rarely":[75,125],"optimized":[77],"without":[78],"regard":[79],"the":[81,213,224,230],"relationship":[82],"between":[83,202],"codes":[84,203],"good":[86],"priors":[88,184],"such":[89,122],"that":[90,104,263],"die":[91],"off":[92],"finally.":[93],"In":[94],"paper,":[96],"inspired":[97],"pretrained":[99,110,152,166,206],"language":[100,106,153,169],"models,":[101],"we":[102,132,162,177,222,236],"find":[103,223],"these":[105,183],"models":[107,154,170],"have":[108],"actually":[109],"superior":[112,218,268],"via":[114],"large":[116],"number":[117],"of":[118],"text":[119,231],"corpus,":[120],"but":[121],"information":[123,243],"exploited":[126],"VQ.":[128],"To":[129,233],"end,":[131,235],"propose":[133],"novel":[135,191],"transfer":[137,147,193],"framework":[138],"vision-to-language":[140,248],"translation,":[141],"called":[142],"VQCT-VLT,":[143],"well-trained":[149],"VQ":[156,273],"for":[157,185,208],"robust":[158,209],"learning.":[160,211,256],"Specifically,":[161],"first":[163],"introduce":[164,237],"part-of-speech":[172],"knowledge":[173],"as":[174,240],"priors.":[175],"Then,":[176],"construct":[178],"vision-related":[180],"achieving":[186],"transfer.":[188],"Finally,":[189],"network":[194],"designed":[196],"exploit":[198],"abundant":[199],"semantic":[200],"relationships":[201],"contained":[204],"codebooks":[207],"Although":[212],"above":[214],"version":[215],"achieve":[217,253],"synthesis":[220],"performance,":[221],"learned":[225],"difficult":[227],"align":[229],"semantics.":[232],"captions":[239],"auxiliary":[241],"supervisory":[242],"then":[245],"design":[246],"translation":[249],"module":[250],"further":[252],"vision-language-aligned":[254],"Experimental":[257],"results":[258],"on":[259],"various":[260],"tasks":[261],"show":[262],"our":[264],"VQCT-VLT":[265],"method":[266],"achieves":[267],"performance":[269],"over":[270],"previous":[271],"state-of-the-art":[272],"methods.":[274]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-02-26T00:00:00"}