{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T04:33:28Z","timestamp":1774326808018,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Funds of China","award":["U20A20183"],"award-info":[{"award-number":["U20A20183"]}]},{"name":"National Science Funds of China","award":["62021001"],"award-info":[{"award-number":["62021001"]}]},{"name":"GPU cluster built by the MCC Laboratory of Information Science and Technology Institution, University of Science and Technology of China (USTC), and the Supercomputing Center of the USTC"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tcsvt.2023.3320688","type":"journal-article","created":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T17:46:34Z","timestamp":1696009594000},"page":"3782-3794","source":"Crossref","is-referenced-by-count":23,"title":["Detect Any Shadow: Segment Anything for Video Shadow Detection"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4741-8231","authenticated-orcid":false,"given":"Yonghui","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9427-9086","authenticated-orcid":false,"given":"Yunyao","family":"Mao","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459163"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0501-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206665"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126331"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459381"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_25"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.819176"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2010.04.003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1233909"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2002.800516"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPHOT.2014.6831803"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00816"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_49"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00778"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00531"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00565"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00466"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00274"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_42"},{"key":"ref21","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv:1704.00675"},{"key":"ref22","article-title":"YouTube-VOS: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv:1809.03327"},{"key":"ref23","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20200"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01007"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049331"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3047977"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3283416"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.51"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/6046.748172"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2002.801448"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2005.15"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2002.1041196"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2004.03.008"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2005.852402"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2009.2013500"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2158335"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2763181"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00312"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref45","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. IEEE Conf. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref48","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref50","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref51","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Assoc. Comput. Linguistics","author":"Devlin"},{"issue":"8","key":"ref52","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"issue":"1","key":"ref54","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref55","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref56","article-title":"Image as a foreign language: BEiT pretraining for all vision and vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2208.10442"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref60","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.563"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00737"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_44"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00374"},{"key":"ref68","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.77"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50835-1_22"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref72","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref73","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Patrick"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10527423\/10267997.pdf?arnumber=10267997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:37:39Z","timestamp":1736368659000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10267997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":73,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3320688","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}