{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:04:43Z","timestamp":1783530283553,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62262094"],"award-info":[{"award-number":["62262094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Xinjiang Uygur Autonomous Region of China","award":["2022D01C56"],"award-info":[{"award-number":["2022D01C56"]}]},{"name":"Xinjiang University Doctor-postgraduate Innovation","award":["XJU2022BS072"],"award-info":[{"award-number":["XJU2022BS072"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3304021","type":"journal-article","created":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T17:44:09Z","timestamp":1691689449000},"page":"2809-2823","source":"Crossref","is-referenced-by-count":38,"title":["MSViT: Training Multiscale Vision Transformers for Image Retrieval"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8553-994X","authenticated-orcid":false,"given":"Xue","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Xinjiang University, Urumqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9181-6720","authenticated-orcid":false,"given":"Jiong","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Xinjiang University, Urumqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7896-1026","authenticated-orcid":false,"given":"Shaochen","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Xinjiang University, Urumqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2087-3496","authenticated-orcid":false,"given":"Hongchun","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2419-2548","authenticated-orcid":false,"given":"Ziyang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Software, Xinjiang University, Urumqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2875304"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097175"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2913513"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940693"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3036779"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451339"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298947"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301269"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10235"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.227"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.598"},{"key":"ref12","first-page":"1711","article-title":"Feature learning based deep supervised hashing with pairwise labels","volume-title":"Proc. 25th Int. Joint Conf. Artif. Intell.","author":"Li","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00134"},{"key":"ref14","first-page":"806","article-title":"Greedy hash: Towards fast optimization for accurate hash coding in CNN","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Su","year":"2018"},{"key":"ref15","article-title":"Push for quantization: Deep fisher hashing","author":"Li","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2900489"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00315"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.037"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/115"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503961.3503968"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2929957"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00989"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3070129"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICICTA51737.2020.00066"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9554838"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref27","first-page":"1","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00353"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298598"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CISP.2015.7407939"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10176"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3222871"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2022.3175605"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3247103"},{"key":"ref36","article-title":"Pyramid self-attention polymerization learning for semi-supervised skeleton-based action recognition","author":"Xu","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3213476"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3222598"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3248170"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref42","article-title":"Training data efficient image transformers & distillation through attention","author":"Touvron","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00986"},{"key":"ref44","article-title":"Training vision transformers for image retrieval","author":"El-Nouby","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531405"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3157517"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298763"},{"key":"ref48","first-page":"647","article-title":"DECAF: A deep convolutional activation feature for generic visual recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Donahue","year":"2013"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10214349.pdf?arnumber=10214349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,12]],"date-time":"2024-02-12T19:24:07Z","timestamp":1707765847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10214349\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3304021","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}