{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T19:52:24Z","timestamp":1769543544816,"version":"3.49.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research &amp; Development Plan of China","award":["2020AAA0106200"],"award-info":[{"award-number":["2020AAA0106200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036012"],"award-info":[{"award-number":["62036012"]}],"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":["62102415"],"award-info":[{"award-number":["62102415"]}],"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":["U21B2044"],"award-info":[{"award-number":["U21B2044"]}],"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":["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":["62072286"],"award-info":[{"award-number":["62072286"]}],"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":["61832002"],"award-info":[{"award-number":["61832002"]}],"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":["62072455"],"award-info":[{"award-number":["62072455"]}],"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":["62002355"],"award-info":[{"award-number":["62002355"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L201001"],"award-info":[{"award-number":["L201001"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Projects of Zhejiang Lab","award":["2022RC0AB02"],"award-info":[{"award-number":["2022RC0AB02"]}]},{"name":"CCF-Hikvision Open Fund","award":["20210004"],"award-info":[{"award-number":["20210004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3207581","type":"journal-article","created":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T15:58:17Z","timestamp":1663603097000},"page":"6329-6340","source":"Crossref","is-referenced-by-count":3,"title":["Weakly-Supervised Video Object Grounding via Learning Uni-Modal Associations"],"prefix":"10.1109","volume":"25","author":[{"given":"Wei","family":"Wang","sequence":"first","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8105-5497","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"ref12","first-page":"2641","article-title":"Flickr30 k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models","author":"plummer","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/149"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.213"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2881114"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3078976"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481539"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01387"},{"key":"ref30","first-page":"18123","article-title":"Counterfactual contrastive learning for weakly-supervised vision-language grounding","volume":"33","author":"zhang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1018-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11161"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00623"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01069"},{"key":"ref1","first-page":"50","article-title":"Weakly-supervised video object grounding from text by loss weighting and object interaction","author":"zhou","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_42"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3046647"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01043"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"5866","DOI":"10.1109\/TPAMI.2020.3046647","article-title":"Weakly supervised object localization and detection: A survey","volume":"44","author":"zhang","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058684"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00597"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.509"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.558"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351074"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00269"},{"key":"ref47","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029008"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00425"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00674"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00177"},{"key":"ref43","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc NAACL-HLT"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00556"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00028"},{"key":"ref7","article-title":"Joint retrieval and generation training for grounded text generation","author":"zhang","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413610"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413614"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475245"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3180025"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09894723.pdf?arnumber=9894723","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T05:56:48Z","timestamp":1769493408000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9894723\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3207581","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}