{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T04:27:07Z","timestamp":1776400027518,"version":"3.51.2"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":["62103420"],"award-info":[{"award-number":["62103420"]}],"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":["62103425"],"award-info":[{"award-number":["62103425"]}],"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":["62103428"],"award-info":[{"award-number":["62103428"]}],"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":["62306329"],"award-info":[{"award-number":["62306329"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"Hunan Natural Science Foundation","doi-asserted-by":"publisher","award":["2023JJ40676"],"award-info":[{"award-number":["2023JJ40676"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"Hunan Natural Science Foundation","doi-asserted-by":"publisher","award":["2021JJ40697"],"award-info":[{"award-number":["2021JJ40697"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"Hunan Natural Science Foundation","doi-asserted-by":"publisher","award":["2021JJ40702"],"award-info":[{"award-number":["2021JJ40702"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcsvt.2024.3407785","type":"journal-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T17:45:40Z","timestamp":1717177540000},"page":"10399-10410","source":"Crossref","is-referenced-by-count":9,"title":["Visual Grounding With Dual Knowledge Distillation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0467-3830","authenticated-orcid":false,"given":"Wansen","family":"Wu","sequence":"first","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8946-4228","authenticated-orcid":false,"given":"Meng","family":"Cao","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8115-7020","authenticated-orcid":false,"given":"Yue","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha, China"}]},{"given":"Yong","family":"Peng","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1245-6622","authenticated-orcid":false,"given":"Long","family":"Qin","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha, China"}]},{"given":"Quanjun","family":"Yin","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2991866"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229081"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-09217-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3174136"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","volume":"1","author":"Devlin"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","volume":"139","author":"Radford"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547756"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref20","article-title":"Real-time referring expression comprehension by single-stage grounding network","volume-title":"arXiv:1812.03426","author":"Chen","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.95"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"ref27","article-title":"YOLOv3: An incremental improvement","volume-title":"arXiv:1804.02767","author":"Redmon","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3594670"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3604557"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3085755"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218587"},{"key":"ref35","article-title":"Fitnets: Hints for thin deep nets","volume-title":"Proc. ICLR","volume":"2","author":"Adriana"},{"key":"ref36","article-title":"Distilling object detectors with task adaptive regularization","volume-title":"arXiv:2006.13108","author":"Sun","year":"2020"},{"key":"ref37","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. ICLR","author":"Gu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.187"},{"key":"ref39","article-title":"CLIP-TD: CLIP targeted distillation for vision-language tasks","volume-title":"arXiv:2201.05729","author":"Wang","year":"2022"},{"key":"ref40","first-page":"1","article-title":"How much can CLIP benefit vision-and-language tasks?","volume-title":"Proc. ICLR","author":"Shen"},{"key":"ref41","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. ICML","volume":"139","author":"Kim"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref43","first-page":"1","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Jaderberg"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_32"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref53","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. ICML","author":"Li"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3285009"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01791"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10739869\/10543065.pdf?arnumber=10543065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:24:04Z","timestamp":1732667044000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10543065\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":56,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3407785","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}