{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:48:12Z","timestamp":1772905692385,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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":["62271239"],"award-info":[{"award-number":["62271239"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022957","name":"Double Thousand Plan of Jiangxi Province","doi-asserted-by":"publisher","award":["JXSQ2023201022"],"award-info":[{"award-number":["JXSQ2023201022"]}],"id":[{"id":"10.13039\/100022957","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tcsvt.2025.3544031","type":"journal-article","created":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T15:44:27Z","timestamp":1740066267000},"page":"7339-7353","source":"Crossref","is-referenced-by-count":4,"title":["Toward Unifying Saliency Transformer for Video Saliency Prediction and Detection"],"prefix":"10.1109","volume":"35","author":[{"given":"Junwen","family":"Xiong","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8867-1031","authenticated-orcid":false,"given":"Chuanyue","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9690-7026","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Huo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0541-8612","authenticated-orcid":false,"given":"Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"Yichun University, Yichun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5013-2501","authenticated-orcid":false,"given":"Yufei","family":"Zha","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777665"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00248"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278410"},{"key":"ref5","article-title":"TransVOS: Video object segmentation with transformers","author":"Mei","year":"2021","journal-title":"arXiv:2106.00588"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00158"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3185252"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2920652"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2906226"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635989"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.38"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00875"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6718"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/35058500"},{"key":"ref18","article-title":"Predicting video saliency with object-to-motion CNN and two-layer convolutional LSTM","author":"Jiang","year":"2017","journal-title":"arXiv:1709.06316"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.80"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2754941"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00342"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01038"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068644"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00394"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321394"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3348659"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00623"},{"key":"ref33","article-title":"Temporal\u2013spatial feature pyramid for video saliency detection","author":"Chang","year":"2021","journal-title":"arXiv:2105.04213"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3194843"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00737"},{"key":"ref36","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988568"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00482"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.242"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2460013"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.273"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3172971"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2022.103700"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.404"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00209"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.487"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3007534"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00830"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_34"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3264883"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110302"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15251-x"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-18408-4"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00061"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3220250"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3139743"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3302911"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11114024\/10896756.pdf?arnumber=10896756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:02:10Z","timestamp":1754503330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10896756\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":62,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3544031","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}