{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:12:02Z","timestamp":1784905922860,"version":"3.55.0"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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":["2020YFB1406604"],"award-info":[{"award-number":["2020YFB1406604"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022955","name":"Fundamental Research Funds for the Provincial Universities of Zhejiang","doi-asserted-by":"publisher","award":["GK229909299001-009"],"award-info":[{"award-number":["GK229909299001-009"]}],"id":[{"id":"10.13039\/100022955","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022955","name":"Fundamental Research Funds for the Provincial Universities of Zhejiang","doi-asserted-by":"publisher","award":["GK219909299001-407"],"award-info":[{"award-number":["GK219909299001-407"]}],"id":[{"id":"10.13039\/100022955","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271180"],"award-info":[{"award-number":["62271180"]}],"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":["62171002"],"award-info":[{"award-number":["62171002"]}],"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":["62031009"],"award-info":[{"award-number":["62031009"]}],"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":["U21B2024"],"award-info":[{"award-number":["U21B2024"]}],"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":["62071415"],"award-info":[{"award-number":["62071415"]}],"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":["62001146"],"award-info":[{"award-number":["62001146"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"\u201cPioneer\u201d and \u201cLeading Goose\u201d Research and Development Program of Zhejiang Province","award":["2022C01068"],"award-info":[{"award-number":["2022C01068"]}]},{"DOI":"10.13039\/501100017600","name":"Zhejiang Province Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023C01046"],"award-info":[{"award-number":["2023C01046"]}],"id":[{"id":"10.13039\/501100017600","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017600","name":"Zhejiang Province Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023C01044"],"award-info":[{"award-number":["2023C01044"]}],"id":[{"id":"10.13039\/501100017600","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Province Natural Science Foundation of China","award":["LZ22F020003"],"award-info":[{"award-number":["LZ22F020003"]}]},{"name":"Zhejiang Province Natural Science Foundation of China","award":["LDT23F01014F01"],"award-info":[{"award-number":["LDT23F01014F01"]}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["D17019"],"award-info":[{"award-number":["D17019"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003467","name":"Hangzhou Dianzi University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003467","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Electronics Corporation DATA (CECDATA) Joint Research Center of Big Data Technologies","award":["KYH063120009"],"award-info":[{"award-number":["KYH063120009"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tcsvt.2023.3278410","type":"journal-article","created":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T18:10:47Z","timestamp":1684779047000},"page":"7696-7707","source":"Crossref","is-referenced-by-count":73,"title":["Transformer-Based Multi-Scale Feature Integration Network for Video Saliency Prediction"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7977-9728","authenticated-orcid":false,"given":"Xiaofei","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3968-3627","authenticated-orcid":false,"given":"Songhe","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9922-3305","authenticated-orcid":false,"given":"Ran","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8788-1725","authenticated-orcid":false,"given":"Bolun","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3730-6401","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3025-0938","authenticated-orcid":false,"given":"Haibing","family":"Yin","sequence":"additional","affiliation":[{"name":"Lishui Institute of Hangzhou Dianzi University, Lishui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9600-8477","authenticated-orcid":false,"given":"Jiyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1204-0512","authenticated-orcid":false,"given":"Chenggang","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2006.05.056"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2669658"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3061153"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2911396"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2978703"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014491"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075470"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2662005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2966453"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2021.3094974"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2936112"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2883305"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6927"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107615"},{"key":"ref15","article-title":"Simple vs complex temporal recurrences for video saliency prediction","author":"Linardos","year":"2019","journal-title":"arXiv:1907.01869"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3139743"},{"key":"ref17","article-title":"Temporal\u2013spatial feature pyramid for video saliency detection","author":"Chang","year":"2021","journal-title":"arXiv:2105.04213"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635989"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.04.010"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01519-y"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref23","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2915033"},{"key":"ref25","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"ref29","article-title":"TransUNet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021","journal-title":"arXiv:2102.04306"},{"key":"ref30","article-title":"Swin-UNet: UNet-like pure transformer for medical image segmentation","author":"Cao","year":"2021","journal-title":"arXiv:2105.05537"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref32","article-title":"Unifying global-local representations in salient object detection with transformer","author":"Ren","year":"2021","journal-title":"arXiv:2108.02759"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3307693"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3127149"},{"key":"ref35","article-title":"Transformer-based network for RGB-D saliency detection","author":"Wang","year":"2021","journal-title":"arXiv:2112.00582"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475601"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104216"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3172971"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2959253"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2019.05.018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3168137"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3051099"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2989158"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3490597"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.01.014"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2829605"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3007534"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00158"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3220250"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12030680"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.01.106"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2870954"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777665"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2754941"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2890749"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3036749"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2906226"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3013162"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115815"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00248"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref70","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3194843"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_25"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366154"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-010-9074-z"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2210727"},{"key":"ref76","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref77","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2815601"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127492"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108120"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.71"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248065"},{"issue":"3","key":"ref85","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"2","author":"Bertasius"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10348119\/10130326.pdf?arnumber=10130326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T01:24:10Z","timestamp":1703035450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10130326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":86,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3278410","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}