{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T05:51:01Z","timestamp":1769061061634,"version":"3.49.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096283","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Robust Video Object Segmentation with Restricted Attention"],"prefix":"10.1109","author":[{"given":"Huaizheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pinxue","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongwen","family":"Le","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_38"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_39"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref30","article-title":"The 2017 davis challenge on video object segmentation","author":"pont-tuset","year":"2017","journal-title":"arXiv preprint arXiv 1704 00675"},{"key":"ref11","first-page":"9481","article-title":"Feelvos: Fast end-to-end embedding learning for video object segmentation","author":"voigtlaender","year":"2019","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref32","first-page":"2793","article-title":"Attention is not all you need: Pure attention loses rank doubly exponentially with depth","author":"dong","year":"2021","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01472"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3196546"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00551"},{"key":"ref16","first-page":"3430","article-title":"Video object segmentation with adaptive feature bank and uncertain-region refinement","volume":"33","author":"liang","year":"2020","journal-title":"Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3137660"},{"key":"ref18","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","author":"cheng","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref24","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref23","article-title":"Associating objects with transformers for video object segmentation","author":"yang","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3219230"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"ref21","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"ref28","article-title":"Youtube-vos: A large-scale video object segmentation benchmark","author":"xu","year":"2018","journal-title":"arXiv preprint arXiv 1809 03327"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547824"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref9","first-page":"565","article-title":"Premvos: Proposal-generation, refinement and merging for video object segmentation","author":"luiten","year":"2018","journal-title":"Asian Conference on Computer Vision"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00891"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_31"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290594"},{"key":"ref5","article-title":"Boosting the transferability of adversarial attacks with global momentum initialization","author":"wang","year":"2022","journal-title":"arXiv preprint arXiv 2211 11236"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096283.pdf?arnumber=10096283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:10Z","timestamp":1700507170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096283\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096283","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}