{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:00:23Z","timestamp":1777568423747,"version":"3.51.4"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"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":["62122010,61876177"],"award-info":[{"award-number":["62122010,61876177"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/cvpr52688.2022.00491","type":"proceedings-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:56:41Z","timestamp":1664308601000},"page":"4954-4963","source":"Crossref","is-referenced-by-count":65,"title":["Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation"],"prefix":"10.1109","author":[{"given":"Zihan","family":"Ding","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianrui","family":"Hui","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junshi","family":"Huang","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Wei","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jizhong","family":"Han","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Si","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref38","first-page":"1","article-title":"Swiftnet: Realtime video object segmentation","author":"wang","year":"0","journal-title":"CVPR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01520"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00830"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/132"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref36","first-page":"1,3,5","article-title":"Context modulated dynamic networks for actor and action video seg-mentation with language queries","author":"wang","year":"0","journal-title":"AAAI"},{"key":"ref35","first-page":"4","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"NeurIPS"},{"key":"ref34","first-page":"2, 5","article-title":"Urvos: Unified referring video object segmentation network with a large-scale benchmark","author":"seo","year":"0","journal-title":"ECCV"},{"key":"ref10","first-page":"2","article-title":"Segmentation from natural language expressions","author":"hu","year":"0","journal-title":"ECCV"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00738"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00417"},{"key":"ref13","first-page":"2","article-title":"Linguistic structure guided context modeling for referring image segmentation","author":"hui","year":"0","journal-title":"ECCV"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref16","first-page":"2, 5","article-title":"Video object segmentation with language referring expressions","author":"khoreva","year":"0","journal-title":"ACCV"},{"key":"ref17","first-page":"6","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref18","first-page":"6","article-title":"Imagenet classification with deep convolutional neural net-works","author":"krizhevsky","year":"2012","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00737"},{"key":"ref28","first-page":"5","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"0","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299035"},{"key":"ref27","first-page":"6","article-title":"Modeling context between objects for referring expression understanding","author":"nagaraja","year":"0","journal-title":"ECCV"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref29","first-page":"1","article-title":"Clip-it! language-guided video summarization","author":"narasimhan","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.alvr-1.8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01656"},{"key":"ref2","first-page":"2","article-title":"Multi-fiber networks for video recognition","author":"chen","year":"0","journal-title":"ECCV"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref20","first-page":"2","article-title":"Referring image segmen-tation via recurrent refinement networks","author":"li","year":"0","journal-title":"CVPR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_13"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7008"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054384"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00996"}],"event":{"name":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"New Orleans, LA, USA","start":{"date-parts":[[2022,6,18]]},"end":{"date-parts":[[2022,6,24]]}},"container-title":["2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9878378\/9878366\/09880159.pdf?arnumber=9880159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:55:38Z","timestamp":1665780938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9880159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/cvpr52688.2022.00491","relation":{},"subject":[],"published":{"date-parts":[[2022,6]]}}}