{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T04:41:54Z","timestamp":1772944914775,"version":"3.50.1"},"reference-count":54,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122010"],"award-info":[{"award-number":["62122010"]}],"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":["61876177"],"award-info":[{"award-number":["61876177"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Zhejiang Province","award":["2022C01082"],"award-info":[{"award-number":["2022C01082"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3181516","type":"journal-article","created":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T19:33:11Z","timestamp":1655407991000},"page":"4266-4277","source":"Crossref","is-referenced-by-count":38,"title":["Progressive Language-Customized Visual Feature Learning for One-Stage Visual Grounding"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2671-0655","authenticated-orcid":false,"given":"Yue","family":"Liao","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}]},{"given":"Aixi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3210-0324","authenticated-orcid":false,"given":"Zhiyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Australian National University, Canberra, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1172-1554","authenticated-orcid":false,"given":"Tianrui","family":"Hui","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Information Engineering, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9180-2935","authenticated-orcid":false,"given":"Si","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2979010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3058614"},{"key":"ref12","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. NeurIPS","author":"Ren"},{"key":"ref13","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"Chen","year":"2018","journal-title":"arXiv:1812.03426"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01384"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref20","first-page":"1","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume-title":"Proc. NIPS","author":"Li"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"ref24","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref25","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"arXiv:1904.07850"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref28","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. NeurIPS","author":"Lu"},{"key":"ref29","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. ICLR","author":"Su"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_35"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. NeurIPS","author":"Vaswani"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2009.03.008"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref47","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3078976"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref50","first-page":"1","article-title":"Interpretable and globally optimal prediction for textual grounding using image concepts","volume-title":"Proc. NeurIPS","author":"Yeh"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_16"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00438"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09798762.pdf?arnumber=9798762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T05:34:24Z","timestamp":1706765664000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9798762\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3181516","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}