{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:25:15Z","timestamp":1778171115633,"version":"3.51.4"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"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":["62122060"],"award-info":[{"award-number":["62122060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Special Fund of the Hubei Luojia Laboratory","award":["220100014"],"award-info":[{"award-number":["220100014"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tcsvt.2023.3292995","type":"journal-article","created":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T19:05:31Z","timestamp":1688756731000},"page":"1228-1240","source":"Crossref","is-referenced-by-count":62,"title":["Multi-Task Learning With Multi-Query Transformer for Dense Prediction"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7098-8419","authenticated-orcid":false,"given":"Yangyang","family":"Xu","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0550-8247","authenticated-orcid":false,"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Nanyang Ave, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9770-7720","authenticated-orcid":false,"given":"Haobo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0530-7231","authenticated-orcid":false,"given":"Yibo","family":"Yang","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0542-2280","authenticated-orcid":false,"given":"Lefei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00873"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00152"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00465"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01557"},{"key":"ref8","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref14","first-page":"8728","article-title":"Adashare: Learning what to share for efficient deep multi-task learning","volume-title":"Proc. NeurIPS","author":"Sun"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00660"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref18","first-page":"12826","article-title":"Learning equivariant segmentation with instance-unique querying","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref20","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. NIPS","author":"Vaswani"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref22","article-title":"ViTAEv2: Vision transformer advanced by exploring inductive bias for image recognition and beyond","author":"Zhang","year":"2022","journal-title":"arXiv:2202.10108"},{"key":"ref23","first-page":"1","article-title":"A dirty model for multi-task learning","volume-title":"Proc. NeurIPS","author":"Jalali"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00457"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00146"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01255"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_43"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00105"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2910151"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00332"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6955"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3216663"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212987"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3215979"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178178"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014889"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995243"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00261"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055780"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3239194"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0271-y"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00969"},{"key":"ref49","first-page":"1","article-title":"Visual recognition with deep nearest centroids","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref50","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. ICLR","author":"Zhu"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref52","first-page":"28522","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. NeurIPS","volume":"34","author":"Xu"},{"key":"ref53","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. ICML","author":"Hugo"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_34"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_31"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_42"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_27"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3230902"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_18"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_30"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100520"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00236"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01831"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref70","article-title":"Automated search for resource-efficient branched multi-task networks","author":"Bruggemann","year":"2020","journal-title":"arXiv:2008.10292"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01068"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10422872\/10176116.pdf?arnumber=10176116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,12]],"date-time":"2024-02-12T20:04:23Z","timestamp":1707768263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10176116\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":72,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3292995","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}