{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T13:51:53Z","timestamp":1784037113946,"version":"3.55.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502120"],"award-info":[{"award-number":["62502120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272130"],"award-info":[{"award-number":["62272130"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2025A1515011674"],"award-info":[{"award-number":["2025A1515011674"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Applied Basic Research Foundation","award":["2025A1515011674"],"award-info":[{"award-number":["2025A1515011674"]}]},{"name":"Applied Basic Research Foundation","award":["62502120"],"award-info":[{"award-number":["62502120"]}]},{"name":"Applied Basic Research Foundation","award":["62272130"],"award-info":[{"award-number":["62272130"]}]},{"name":"Shenzhen Peacock Program","award":["ZX20230597"],"award-info":[{"award-number":["ZX20230597"]}]},{"name":"Nature Science Program of Shenzhen Shenzhen Science and Technology Program","award":["ZDCYKCX20250901092700001"],"award-info":[{"award-number":["ZDCYKCX20250901092700001"]}]},{"name":"Nature Science Program of Shenzhen Shenzhen Science and Technology Program","award":["SYSPG20241211173609009"],"award-info":[{"award-number":["SYSPG20241211173609009"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2025YFE0103100"],"award-info":[{"award-number":["2025YFE0103100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tpami.2026.3667935","type":"journal-article","created":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T20:56:17Z","timestamp":1772052977000},"page":"7656-7673","source":"Crossref","is-referenced-by-count":1,"title":["Codebook Transfer With Vision-to-Language Translation for Vector Quantization"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6178-6797","authenticated-orcid":false,"given":"Baoquan","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8935-8322","authenticated-orcid":false,"given":"Guotao","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianran","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1807-8581","authenticated-orcid":false,"given":"Yunming","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Wen","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaochen","family":"Qi","sequence":"additional","affiliation":[{"name":"ShenZhen SiFar Co., Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"He","sequence":"additional","affiliation":[{"name":"ShenZhen SiFar Co., Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref2","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref3","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Den"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01063"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01771"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02084"},{"key":"ref10","first-page":"19822","article-title":"CogView: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref11","article-title":"Theory and experiments on vector quantized autoencoders","author":"Roy","year":"2018"},{"key":"ref12","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Razavi"},{"key":"ref13","first-page":"4524","article-title":"Hierarchical quantized autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Williams"},{"key":"ref14","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020"},{"key":"ref15","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2019"},{"key":"ref16","article-title":"SQ-VAE: Variational bayes on discrete representation with self-annealed stochastic quantization","author":"Takida","year":"2022"},{"key":"ref17","article-title":"Vector quantized Wasserstein auto-encoder","author":"Vuong","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"issue":"8","key":"ref19","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00375"},{"key":"ref23","first-page":"4847","article-title":"Adaptive cross-modal few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xing"},{"key":"ref24","article-title":"Exploring models and data for image question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3366154"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3303451"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00741"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00199"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01822"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1701"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref35","article-title":"Vector-quantized image modeling with improved VQGAN","author":"Yu","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02164"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00729"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4433"},{"key":"ref39","article-title":"Scaling the codebook size of VQGAN to 100,000 with a utilization rate of 99%","author":"Zhu","year":"2024"},{"key":"ref40","first-page":"14096","article-title":"Straightening out the straight-through estimator: Overcoming optimization challenges in vector quantized networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huh"},{"key":"ref41","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021"},{"key":"ref42","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3460180"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339661"},{"key":"ref45","first-page":"4382","article-title":"Language quantized autoencoders: Towards unsupervised text-image alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref46","article-title":"SPAE: Semantic pyramid autoencoder for multimodal generation with frozen LLMs","author":"Yu","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02554"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3277881"},{"key":"ref49","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref50","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00384"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00273"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00274"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28311"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref58","article-title":"The caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref60","first-page":"1","article-title":"Restructuring vector quantization with the rotation trick","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Fifty"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref64","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref65","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref66","article-title":"A formal evaluation of PSNR as quality measurement parameter for image segmentation algorithms","author":"Fardo","year":"2016"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3125459"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296823"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3343736"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328185"},{"key":"ref77","article-title":"ClipCap: Clip prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328298"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3115\/981732.981751"},{"key":"ref84","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. IEEE Eur. Symp. Secur. Privacy","author":"Lu"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11552636\/11410589.pdf?arnumber=11410589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:52:15Z","timestamp":1780948335000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11410589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":84,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3667935","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}