{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T13:53:51Z","timestamp":1780926831352,"version":"3.54.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["61902139"],"award-info":[{"award-number":["61902139"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3141891","type":"journal-article","created":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T20:36:17Z","timestamp":1641933377000},"page":"1964-1978","source":"Crossref","is-referenced-by-count":30,"title":["Transformer-Based Efficient Salient Instance Segmentation Networks With Orientative Query"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2630-2838","authenticated-orcid":false,"given":"Jialun","family":"Pei","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyang","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8454-1407","authenticated-orcid":false,"given":"He","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8006-7851","authenticated-orcid":false,"given":"Chuanbo","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.70"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00933"},{"key":"ref3","first-page":"7222","article-title":"Joint learning of saliency detection and weakly supervised semantic segmentation","volume-title":"Proc. IEEE \/CVF Int. Conf. Comput. Vis.","author":"Zeng","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3069297"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.31"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00403"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3051099"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.34"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2612175"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.012"},{"key":"ref12","first-page":"597","article-title":"Online tracking by learning discriminative saliency map with convolutional neural network","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hong","year":"2015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00626"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3065822"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref18","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref20","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_31"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-019-0149-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.407"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298731"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.563"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00887"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3073564"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3058788"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924578"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3060412"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2940851"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.618"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.153"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299184"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_12"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.151"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.404"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref46","first-page":"2980","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref47","first-page":"10183","article-title":"Synthesizer: Rethinking self-attention in transformer models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tay","year":"2021"},{"key":"ref48","article-title":"A survey on visual transformer","author":"Han","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00374"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996406"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013159"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995676"},{"key":"ref62","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref63","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist. JMLR Workshop Conf. Proc.","author":"Glorot","year":"2010"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.370"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01304"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09678049.pdf?arnumber=9678049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:24:59Z","timestamp":1705184699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9678049\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3141891","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}