{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T08:35:20Z","timestamp":1770194120902,"version":"3.49.0"},"reference-count":51,"publisher":"Tsinghua University Press","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.26599\/cvm.2025.9450427","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T20:57:32Z","timestamp":1769201852000},"page":"189-202","source":"Crossref","is-referenced-by-count":0,"title":["Language Interprets Vision: Adaptive Encoding and Decoding for Referring Image Segmentation"],"prefix":"10.26599","volume":"12","author":[{"given":"Qi","family":"A","sequence":"first","affiliation":[{"name":"Space Star Technology Co., Ltd.,Beijing,China,100095"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanyuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing Institute of Technology,Beijing,China,100081"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingping","family":"Dong","sequence":"additional","affiliation":[{"name":"Inception Institute of Artificial Intelligence,Abu Dhabi,UAE,999041"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Macau,State Key Laboratory of Internet of Things for Smart City,Department of Computer and Information Science,Macau,China,999078"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"11138","reference":[{"key":"ref1","article-title":"Recurrent instance segmentation using sequences of referring expressions","author":"Herrera-Palacio","year":"2019","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref9","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_23"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref19","article-title":"Referring expression object segmentation with caption-aware consistency","author":"Chen","year":"2019","journal-title":"ar Xiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2971171"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506483"},{"key":"ref25","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","author":"Li","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref28","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref30","volume-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref31","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Brown","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref33","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01322"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref37","article-title":"How to understand masked autoencoders","author":"Cao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9096-9"},{"key":"ref39","article-title":"Breaking the curse of dimensionality with convex neural networks","author":"Bach","year":"2016","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.066"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163578"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref51","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/11370641\/11363134.pdf?arnumber=11363134","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T20:54:31Z","timestamp":1770152071000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11363134\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":51,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.26599\/cvm.2025.9450427","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}