{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T08:44:39Z","timestamp":1778575479867,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["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":["62322212"],"award-info":[{"award-number":["62322212"]}],"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"}]},{"name":"Peng Cheng Laboratory Research","award":["PCL2023AS6-1"],"award-info":[{"award-number":["PCL2023AS6-1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3321501","type":"journal-article","created":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T18:00:45Z","timestamp":1696269645000},"page":"4334-4347","source":"Crossref","is-referenced-by-count":61,"title":["CLIP-VG: Self-Paced Curriculum Adapting of CLIP for Visual Grounding"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2592-5264","authenticated-orcid":false,"given":"Linhui","family":"Xiao","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-9755","authenticated-orcid":false,"given":"Xiaoshan","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3948-7413","authenticated-orcid":false,"given":"Fang","family":"Peng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4959-8878","authenticated-orcid":false,"given":"Ming","family":"Yan","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref8","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"Chen","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3139467"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3096087"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00425"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00269"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00556"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01387"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00641"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00476"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.10.079"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01507"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01838"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.303"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25085-9_1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.558"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058684"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00226"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CRV55824.2022.00015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"ref43","article-title":"Adapting clip for phrase localization without further training","author":"Li","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467206"},{"key":"ref45","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref46","first-page":"23318","article-title":"Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014951"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref51","article-title":"Pseudo-labeling curriculum for unsupervised domain adaptation","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Choi","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16852"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3121986"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1486"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2563981"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"ref57","first-page":"1189","article-title":"Self-paced learning for latent variable models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Kumar","year":"2010"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3268066"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref62","article-title":"Clipcap: Clip prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00270"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351074"},{"key":"ref66","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859880"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10269126.pdf?arnumber=10269126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T18:51:12Z","timestamp":1710269472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10269126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3321501","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}