{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T16:02:24Z","timestamp":1778688144134,"version":"3.51.4"},"reference-count":108,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tpami.2024.3484658","type":"journal-article","created":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T13:26:39Z","timestamp":1729603599000},"page":"1042-1055","source":"Crossref","is-referenced-by-count":18,"title":["Prompt Tuning of Deep Neural Networks for Speaker-Adaptive Visual Speech Recognition"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6514-0018","authenticated-orcid":false,"given":"Minsu","family":"Kim","sequence":"first","affiliation":[{"name":"Image and Video Systems Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6425-549X","authenticated-orcid":false,"given":"Hyung-Il","family":"Kim","sequence":"additional","affiliation":[{"name":"Visual Intelligence Research Section, Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5306-6853","authenticated-orcid":false,"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"Image and Video Systems Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.173"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027960"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/34.982900"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.303"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3115626"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.20003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref11","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-813445-0.00005-8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.127"},{"key":"ref14","article-title":"LipNet: End-to-end sentence-level lipreading","author":"Assael","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190780"},{"key":"ref16","first-page":"2758","article-title":"Lip to speech synthesis with visual context attentional GAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506396"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_33"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1995-411"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596119"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-490"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003751"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053104"},{"key":"ref24","article-title":"Adversarial reprogramming of neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Elsayed"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482053"},{"key":"ref26","article-title":"Improved input reprogramming for GAN conditioning","author":"Dinh","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.02.086"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00295"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3217375"},{"key":"ref30","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref36","first-page":"24631","article-title":"Prompting decision transformer for few-shot policy generalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref40","article-title":"Visual prompt tuning for test-time domain adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gao"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2346313"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2457612"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-336"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.223"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.251"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1416343"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.08.005"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref54","article-title":"Learning spatio-temporal features with two-stream deep 3D CNNs for lipreading","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Weng"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00132"},{"key":"ref56","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.09.003"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2921539"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00036"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref63","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6174"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01312"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref71","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-214"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472172"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675351"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3237"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01926"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref86","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref87","article-title":"Exploring visual prompts for adapting large-scale models","author":"Bahng","year":"2022"},{"key":"ref88","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref89","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660001"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref92","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.494"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11311"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001412660024"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.55"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref99","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref100","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461932"},{"key":"ref102","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref103","article-title":"Towards a unified view of parameter-efficient transfer learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He"},{"key":"ref104","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref105","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.666"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10835210\/10726873.pdf?arnumber=10726873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:43:32Z","timestamp":1755546212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10726873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":108,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3484658","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":[[2025,2]]}}}