{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T01:35:14Z","timestamp":1743384914778,"version":"3.30.2"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/avss61716.2024.10672595","type":"proceedings-article","created":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T17:51:42Z","timestamp":1726681902000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["RefMOS: A Robust Referred Moving Object Segmentation framework based on text query"],"prefix":"10.1109","author":[{"given":"Prafulla","family":"Saxena","sequence":"first","affiliation":[{"name":"MNIT Jaipur"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Susim Mukul","family":"Roy","sequence":"additional","affiliation":[{"name":"IIT Jodhpur"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh Kumar","family":"Tyagi","sequence":"additional","affiliation":[{"name":"MNIT Jaipur"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Santosh Kumar","family":"Vipparthi","sequence":"additional","affiliation":[{"name":"IIT Ropar"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subrahmanyam","family":"Murala","sequence":"additional","affiliation":[{"name":"IIT Ropar"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Balasubramanian","sequence":"additional","affiliation":[{"name":"IIT Roorkee"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2900426"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13413-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref5","first-page":"11781","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00774"},{"key":"ref7","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093333"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20017"},{"key":"ref11","article-title":"Rethinking cross-modal interaction from a top-down perspective for referring video object segmentation","author":"Liang","year":"2021","journal-title":"arXiv preprint arXiv:2106.01061"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545504"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00817"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2880096"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref18","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv preprint arXiv:1704.00675"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897970"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref24","article-title":"Youtube-vos: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv preprint arXiv:1809.03327"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"}],"event":{"name":"2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,16]]}},"container-title":["2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10672516\/10672563\/10672595.pdf?arnumber=10672595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T19:21:23Z","timestamp":1734549683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10672595\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/avss61716.2024.10672595","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}