{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T08:54:05Z","timestamp":1780736045075,"version":"3.54.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2017YFE0104100"],"award-info":[{"award-number":["2017YFE0104100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62132016"],"award-info":[{"award-number":["62132016"]}],"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":["62171343"],"award-info":[{"award-number":["62171343"]}],"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":["62071361"],"award-info":[{"award-number":["62071361"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"Key Research and Development Program of Shaanxi","doi-asserted-by":"publisher","award":["2021ZDLGY01-03"],"award-info":[{"award-number":["2021ZDLGY01-03"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZDRC2102"],"award-info":[{"award-number":["ZDRC2102"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3161832","type":"journal-article","created":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T19:46:11Z","timestamp":1648583171000},"page":"2839-2849","source":"Crossref","is-referenced-by-count":18,"title":["Object-Agnostic Transformers for Video Referring Segmentation"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0405-6816","authenticated-orcid":false,"given":"Xu","family":"Yang","sequence":"first","affiliation":[{"name":"School of Electronic Engineering, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3048-8268","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5535-0898","authenticated-orcid":false,"given":"De","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2620-3247","authenticated-orcid":false,"given":"Cheng","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref32","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","author":"li","year":"2021","journal-title":"arXiv 2106 03089"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref30","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc ACL"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref35","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"huang","year":"2020","journal-title":"arXiv 2004 00849"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"ref40","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv 1609 08144"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/132"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6895"},{"key":"ref18","first-page":"667","article-title":"Dynamic filter networks","author":"xu","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3127562"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3057872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984373"},{"key":"ref29","article-title":"Actor and action modular network for text-based video segmentation","author":"yang","year":"2020","journal-title":"arXiv 2011 00786"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019030"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.219"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2998297"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083089"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3082298"},{"key":"ref20","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.336"},{"key":"ref21","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"li","year":"2019","journal-title":"arXiv 1908 03557"},{"key":"ref42","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.115"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3052086"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3102955"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3087413"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09744457.pdf?arnumber=9744457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:37:45Z","timestamp":1652733465000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9744457\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3161832","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}