{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:47:10Z","timestamp":1777657630386,"version":"3.51.4"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003816","name":"Huawei Technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/cvpr52729.2023.02189","type":"proceedings-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T17:30:52Z","timestamp":1692725452000},"page":"22857-22866","source":"Crossref","is-referenced-by-count":27,"title":["Mask-Free Video Instance Segmentation"],"prefix":"10.1109","author":[{"given":"Lei","family":"Ke","sequence":"first","affiliation":[{"name":"ETH Zürich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Danelljan","sequence":"additional","affiliation":[{"name":"ETH Zürich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[{"name":"ETH Zürich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Wing","family":"Tai","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Keung","family":"Tang","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fisher","family":"Yu","sequence":"additional","affiliation":[{"name":"ETH Zürich"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Weakly supervised instance segmentation using the bounding box tightness prior","author":"hsu","year":"0","journal-title":"NeurIPS"},{"key":"ref57","article-title":"Seqformer: a frustratingly simple model for video instance segmentation","author":"wu","year":"0","journal-title":"ECCV"},{"key":"ref12","article-title":"Vita: Video instance segmentation via object token association","author":"heo","year":"0","journal-title":"NeurIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"ref15","article-title":"Video instance segmentation using inter-frame communication transformers","author":"hwang","year":"0","journal-title":"NeurIPS"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00103"},{"key":"ref14","article-title":"Minvis: A minimal video instance segmentation framework without video-based training","author":"huang","year":"0","journal-title":"NeurIPS"},{"key":"ref58","article-title":"defense of online models for video instance segmentation","author":"wu","year":"0","journal-title":"ECCV"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00813"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_46"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref10","article-title":"Inspro: Propagating instance query and proposal for online video instance segmentation","author":"he","year":"0","journal-title":"NeurIPS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref17","article-title":"Video mask transfiner for high-quality video instance segmentation","author":"ke","year":"0","journal-title":"ECCV"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00437"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00401"},{"key":"ref18","article-title":"Prototypical cross-attention networks for multiple object tracking and segmentation","author":"ke","year":"0","journal-title":"NeurIPS"},{"key":"ref51","article-title":"Learning semantic segmentation with weakly-annotated videos","author":"tokmakov","year":"0","journal-title":"ECCV"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"ref46","article-title":"Video instance segmentation via multi-scale spatiotemporal split attention transformer","author":"thawakar","year":"0","journal-title":"ECCV"},{"key":"ref45","article-title":"Raft: Recurrent all-pairs field transforms for optical flow","author":"teed","year":"0","journal-title":"ECCV"},{"key":"ref48","article-title":"Conditional convolutions for instance segmentation","author":"tian","year":"0","journal-title":"ECCV"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00342"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015720"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00325"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.232"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.191"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00264"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00857"},{"key":"ref4","article-title":"Sipmask: Spatial information preservation for fast image and video instance segmentation","author":"cao","year":"0","journal-title":"ECCV"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref6","article-title":"Mask2former for video instance segmentation","author":"cheng","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref5","article-title":"End-to-end object detection with transformers","author":"carion","year":"0","journal-title":"ECCV"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2621185"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299178"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.203"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00969"},{"key":"ref30","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"0","journal-title":"ECCV"},{"key":"ref33","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"0","journal-title":"ICLRE"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01375"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00976"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_10"},{"key":"ref39","article-title":"Occluded video instance segmentation: A benchmark","author":"qi","year":"2021","journal-title":"IJCV"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537320"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00691"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00339"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01106"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00267"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.181"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_18"},{"key":"ref21","article-title":"Conditional object-centric learning from video","author":"kipf","year":"0","journal-title":"ICLRE"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01316"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00176"},{"key":"ref60","article-title":"Towards grand unification of object tracking","author":"yan","year":"0","journal-title":"ECCV"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00794"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"}],"event":{"name":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2023,6,17]]},"end":{"date-parts":[[2023,6,24]]}},"container-title":["2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10203037\/10203050\/10203650.pdf?arnumber=10203650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T18:01:22Z","timestamp":1694455282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10203650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/cvpr52729.2023.02189","relation":{},"subject":[],"published":{"date-parts":[[2023,6]]}}}