{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:39:01Z","timestamp":1778258341627,"version":"3.51.4"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Key Research Program of Frontier Sciences Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["ZDBS-LY-JSC032"],"award-info":[{"award-number":["ZDBS-LY-JSC032"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61721004"],"award-info":[{"award-number":["61721004"]}],"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":["U1803261"],"award-info":[{"award-number":["U1803261"]}],"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":["61976132"],"award-info":[{"award-number":["61976132"]}],"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":["61922015"],"award-info":[{"award-number":["61922015"]}],"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":["U19B2036"],"award-info":[{"award-number":["U19B2036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["Z201100006820079"],"award-info":[{"award-number":["Z201100006820079"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chinese Academy of Sciences-Artificial Intelligence Research"},{"DOI":"10.13039\/501100005089","name":"Beijing Natural Science Foundation Project","doi-asserted-by":"publisher","award":["Z200002"],"award-info":[{"award-number":["Z200002"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011222","name":"Open Projects Program of National Laboratory of Pattern Recognition","doi-asserted-by":"publisher","award":["202100028"],"award-info":[{"award-number":["202100028"]}],"id":[{"id":"10.13039\/501100011222","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3185487","type":"journal-article","created":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T20:00:49Z","timestamp":1656446449000},"page":"4474-4489","source":"Crossref","is-referenced-by-count":13,"title":["Actor and Action Modular Network for Text-Based Video Segmentation"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5455-1874","authenticated-orcid":false,"given":"Jianhua","family":"Yang","sequence":"first","affiliation":[{"name":"Pattern Recognition and Intelligent Systems Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8239-7229","authenticated-orcid":false,"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Niu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9701-6487","authenticated-orcid":false,"given":"Linjiang","family":"Huang","sequence":"additional","affiliation":[{"name":"Multimedia Laboratory, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2950-2488","authenticated-orcid":false,"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent Systems Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383132"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35749-7_17"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.336"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2759504"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.219"},{"key":"ref9","article-title":"Actor-action semantic segmentation with region masks","author":"Dang","year":"2018","journal-title":"arXiv:1807.08430"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_43"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00300"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.115"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00992"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6895"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00996"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018401"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3391743"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2811621"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref37","first-page":"630","article-title":"Dynamic multimodal instance segmentation guided by natural language queries","volume-title":"Proc. ECCV","author":"Margffoytuay"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054384"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506483"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref46","first-page":"455","article-title":"Parsing with compositional vector grammars","volume-title":"Proc. ACL","author":"Socher"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1181"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref52","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. BMVC","author":"Faghri"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.228"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00125"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01164-6"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00982"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09810121.pdf?arnumber=9810121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:47:08Z","timestamp":1706759228000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9810121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3185487","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}