{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:16Z","timestamp":1777888696309,"version":"3.51.4"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["61972217,32071459,62176249,62006133,62271465,62406167,U24B6012"],"award-info":[{"award-number":["61972217,32071459,62176249,62006133,62271465,62406167,U24B6012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02086","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22467-22476","source":"Crossref","is-referenced-by-count":0,"title":["Temporal-Aware Query Routing for Real-Time Video Instance Segmentation"],"prefix":"10.1109","author":[{"given":"Zesen","family":"Cheng","sequence":"first","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kehan","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yian","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation and BNRist,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.309"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_10"},{"key":"ref3","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Conditional computation in neural networks for faster models","author":"Bengio","year":"2015","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00976"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"ref8","first-page":"213","article-title":"End-toend object detection with transformers","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Carion","year":"2020"},{"key":"ref9","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1565"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.ngt-1.3"},{"key":"ref13","article-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","volume-title":"arXiv preprint","year":"2023"},{"key":"ref14","article-title":"An image is worth 16 \\times 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Depth-adaptive transformer","author":"Elbayad","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1679"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01405"},{"key":"ref19","article-title":"Minvis: A minimal video instance segmentation framework without video-based training","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"ref21","first-page":"13352","article-title":"Video instance segmentation using inter-frame communication transformers","volume":"34","author":"Hwang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_42"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00437"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0357"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01106"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.537"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","article-title":"Novis: A case for end-to-end near-online video instance segmentation","author":"Meinhardt","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00198"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1269"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.593"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref38","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref39","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref40","article-title":"Idk cascades: Fast deep learning by learning not to overthink","author":"Wang","year":"2017","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref46","article-title":"The 3rd large-scale video object segmentation challenge - video instance segmentation track, 2021","author":"Yang","journal-title":"5"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref50","article-title":"Learning to skip for language modeling","author":"Zeng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00124"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3552694"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_26"},{"key":"ref54","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Zhu","year":"2020"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444953.pdf?arnumber=11444953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:00Z","timestamp":1777611300000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444953\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02086","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}