{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:13Z","timestamp":1792786933952,"version":"4.5.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"New Generation Artificial Intelligence-National Science and Technology Major Project","award":["2025ZD0123601"],"award-info":[{"award-number":["2025ZD0123601"]}]},{"name":"Chongqing Postdoctoral Research Special Funding Project","award":["2024CQBSHTB3015"],"award-info":[{"award-number":["2024CQBSHTB3015"]}]},{"name":"National Natural Science Foundation of China","award":["62221005"],"award-info":[{"award-number":["62221005"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Natural Science Foundation of Chongqing","award":["CSTB2024NSCQ-QCXMX0060"],"award-info":[{"award-number":["CSTB2024NSCQ-QCXMX0060"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3655505","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:55:34Z","timestamp":1768856134000},"page":"4069-4083","source":"Crossref","is-referenced-by-count":0,"title":["M-STEP: Multi-Scale Temporal Information Enhancement and Propagation for Hierarchical Visual Transformer Tracking"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6705-4757","authenticated-orcid":false,"given":"Yang","family":"Fang","sequence":"first","affiliation":[{"name":"Chongqing University of Posts and Telecommunications","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0850-4591","authenticated-orcid":false,"given":"Yujie","family":"Wang","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3153-6125","authenticated-orcid":false,"given":"Bingbing","family":"Jiang","sequence":"additional","affiliation":[{"name":"Hangzhou Normal University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8267-6834","authenticated-orcid":false,"given":"Zongyi","family":"Xu","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2802-8139","authenticated-orcid":false,"given":"Jiaxu","family":"Leng","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3662-9380","authenticated-orcid":false,"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9033-8245","authenticated-orcid":false,"given":"Weisheng","family":"Li","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7985-0037","authenticated-orcid":false,"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[{"name":"Chongqing University of Posts and Telecommunications","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2606"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01732-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/61"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12296"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3291140"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1218"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"issue":"59","key":"ref16","first-page":"1","article-title":"SPPT: Siamese pyramid pooling transformer for visual object tracking","volume":"13","author":"Fang","year":"2023","journal-title":"Hum.-Centric Comput. Inf. Sci."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3285441"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02186"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00928"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28192"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3321476"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3347644"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3321497"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28286"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0476"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref40","first-page":"1","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Alexey","year":"2021"},{"key":"ref41","first-page":"1","article-title":"HiViT: A simpler and more efficient design of hierarchical vision transformer","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Zhang","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref44","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref45","first-page":"2024","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. 1st Conf. Lang. Modeling","author":"Gu"},{"key":"ref46","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Krizhevsky","year":"2012"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4157"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3428316"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01822"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107304"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3398405"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3264851"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00525"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25085-9_25"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11358797.pdf?arnumber=11358797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T19:10:28Z","timestamp":1790622628000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11358797\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3655505","relation":{},"ISSN":["1941-0077","1520-9210"],"issn-type":[{"value":"1941-0077","type":"electronic"},{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}