{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T04:50:59Z","timestamp":1790052659817,"version":"4.0.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["61831005"],"award-info":[{"award-number":["61831005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61525102"],"award-info":[{"award-number":["61525102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971095"],"award-info":[{"award-number":["61971095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871078"],"award-info":[{"award-number":["61871078"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.2991504","type":"journal-article","created":{"date-parts":[[2020,4,30]],"date-time":"2020-04-30T19:54:57Z","timestamp":1588276497000},"page":"995-1007","source":"Crossref","is-referenced-by-count":28,"title":["Query Reconstruction Network for Referring Expression Image Segmentation"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1340-0009","authenticated-orcid":false,"given":"Hengcan","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7481-095X","authenticated-orcid":false,"given":"Hongliang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2936-6340","authenticated-orcid":false,"given":"Qingbo","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1946-3235","authenticated-orcid":false,"given":"King Ngi","family":"Ngan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref33","article-title":"Utilizing large scale vision and text datasets for image segmentation from referring expressions","author":"hu","year":"2016","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref31","first-page":"272","article-title":"Searching for ambiguous objects in videos using relational referring expressions","author":"anayurt","year":"2019","journal-title":"Proc Brit Mach Vision Conf"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.520"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.122"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00254"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.347"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2812600"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.140"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref54","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2942480"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref14","first-page":"4980","article-title":"RDFNET: RGB-D multi-level residual feature fusion for indoor semantic segmentation","author":"park","year":"0","journal-title":"Proc IEEE Int Conf Comput Vision"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.224"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.147"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240657"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"2545","DOI":"10.1109\/TMM.2017.2703089","article-title":"Learning efficient binary codes from high-level feature representations for multi-label image retrieval","volume":"19","author":"lei","year":"2017","journal-title":"IEEE Trans Multimedia"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751140"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2739919"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2671447"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref49","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"ref48","first-page":"263","article-title":"Referring expression object segmentation with caption-aware consistency","author":"chen","year":"0","journal-title":"Proc Brit Mach Vision Conf"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref43","first-page":"820","article-title":"Dual learning for machine translation","author":"he","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09082867.pdf?arnumber=9082867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:37Z","timestamp":1652194297000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9082867\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.2991504","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}