{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T13:03:09Z","timestamp":1791291789852,"version":"4.1.0"},"reference-count":70,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3403497","type":"journal-article","created":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T13:26:49Z","timestamp":1716816409000},"page":"3369-3384","source":"Crossref","is-referenced-by-count":12,"title":["Toward High Quality Multi-Object Tracking and Segmentation Without Mask Supervision"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7822-5216","authenticated-orcid":false,"given":"Wensheng","family":"Cheng","sequence":"first","affiliation":[{"name":"Department of Computer Science, Stony Brook University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wu","sequence":"additional","affiliation":[{"name":"Wormpex AI Research LLC, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7183-6943","authenticated-orcid":false,"given":"Zhenyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Wormpex AI Research LLC, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4094-8413","authenticated-orcid":false,"given":"Haibin","family":"Ling","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stony Brook University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9522-6157","authenticated-orcid":false,"given":"Gang","family":"Hua","sequence":"additional","affiliation":[{"name":"Wormpex AI Research LLC, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00904"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00231"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_10"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00976"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2985815"},{"key":"ref8","article-title":"Mask2former for video instance segmentation","author":"Cheng","year":"2021","journal-title":"arXiv:2112.10764"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00264"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.U09\/CVPR.2019.00552"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.07737"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref18","first-page":"13352","article-title":"Video instance segmentation using inter-frame communication transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hwang"},{"key":"ref19","first-page":"667","article-title":"Dynamic filter networks","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"29","author":"Jia"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02189"},{"key":"ref23","first-page":"1192","article-title":"Prototypical cross-attention networks for multiple object tracking and segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ke"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref26","article-title":"Where are the masks: Instance segmentation with image-level supervision","author":"Laradji","year":"2019","journal-title":"arXiv:1907.01430"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00176"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01375"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969183"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1606.04797"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"ref37","article-title":"The 2017 DAVIS challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv:1704.00675"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00688"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"ref42","first-page":"2373","article-title":"Learning the local statistics of optical flow","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rosenbaum"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW52041.2021.00018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00747"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref46","first-page":"507","article-title":"On regularized losses for weakly-supervised CNN segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Tang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104471"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00813"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185628"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"ref59","article-title":"YouTube-VOS: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv:1809.03327"},{"key":"ref60","volume-title":"YouTube-VIS Dataset 2021 Version","author":"Xu","year":"2021"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087898"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_16"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202574"},{"key":"ref65","first-page":"1307","article-title":"CondConv: Conditionally parameterized convolutions for efficient inference","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10539628.pdf?arnumber=10539628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T00:48:18Z","timestamp":1717721298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10539628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3403497","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}