{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:12:43Z","timestamp":1778166763022,"version":"3.51.4"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFE0200300"],"award-info":[{"award-number":["2022YFE0200300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972323"],"award-info":[{"award-number":["61972323"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Program Special Fund in Xi\u2019an Jiaotong-Liverpool University","award":["KSF-T-02"],"award-info":[{"award-number":["KSF-T-02"]}]},{"name":"Key Program Special Fund in Xi\u2019an Jiaotong-Liverpool University","award":["KSF-P-02"],"award-info":[{"award-number":["KSF-P-02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tcsvt.2023.3263468","type":"journal-article","created":{"date-parts":[[2023,3,31]],"date-time":"2023-03-31T17:58:14Z","timestamp":1680285494000},"page":"5999-6012","source":"Crossref","is-referenced-by-count":20,"title":["Fully and Weakly Supervised Referring Expression Segmentation With End-to-End Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8945-5391","authenticated-orcid":false,"given":"Hui","family":"Li","sequence":"first","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjie","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9416-2486","authenticated-orcid":false,"given":"Jimin","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0199-7386","authenticated-orcid":false,"given":"Eng Gee","family":"Lim","sequence":"additional","affiliation":[{"name":"School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00195"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2686857"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref53","first-page":"17721","article-title":"SOLOv2: Dynamic and fast instance segmentation","author":"wang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.066"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6971"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.344"},{"key":"ref19","first-page":"1","article-title":"Weakly-supervised salient instance detection","author":"tian","year":"2020","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083269"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3057503"},{"key":"ref50","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref46","first-page":"123","article-title":"Video object segmentation with language referring expressions","author":"khoreva","year":"2018","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058684"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3098118"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref7","article-title":"Cross-modal recurrent semantic comprehension for referring image segmentation","author":"shang","year":"2022","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/132"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3030656"},{"key":"ref35","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"su","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref36","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3073718"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882225"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref72","article-title":"Gated CRF loss for weakly supervised semantic image segmentation","author":"obukhov","year":"2019","journal-title":"arXiv 1906 04651"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2100463"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16434"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref63","first-page":"549","article-title":"What’s the point: Semantic segmentation with point supervision","author":"bearman","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref61","first-page":"1","article-title":"An intriguing failing of convolutional neural networks and the CoordConv solution","author":"liu","year":"2018","journal-title":"Proc Adv Neural Inform Process Syst"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10269772\/10089870.pdf?arnumber=10089870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:31:04Z","timestamp":1698085864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10089870\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":73,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3263468","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}