{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T04:20:51Z","timestamp":1769833251257,"version":"3.49.0"},"reference-count":68,"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":[{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2008085QF325"],"award-info":[{"award-number":["2008085QF325"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2008085QF314"],"award-info":[{"award-number":["2008085QF314"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"National University of Defense Technology through the Scientific Research Project","doi-asserted-by":"publisher","award":["zk19-15"],"award-info":[{"award-number":["zk19-15"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation of Army Artillery and Air Defense Academy of PLA","award":["PFXY220114001"],"award-info":[{"award-number":["PFXY220114001"]}]},{"name":"Anhui Province Laboratory of Advanced Laser Technology","award":["ky19c604"],"award-info":[{"award-number":["ky19c604"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Instrum. Meas."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tim.2023.3324362","type":"journal-article","created":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T17:54:00Z","timestamp":1697219640000},"page":"1-11","source":"Crossref","is-referenced-by-count":13,"title":["Visual Grounding With Joint Multimodal Representation and Interaction"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2841-7129","authenticated-orcid":false,"given":"Hong","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8005-7182","authenticated-orcid":false,"given":"Qingyang","family":"Lu","sequence":"additional","affiliation":[{"name":"Army Artillery and Air Defense Academy of PLA, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7355-9668","authenticated-orcid":false,"given":"Lei","family":"Xue","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0368-0210","authenticated-orcid":false,"given":"Mogen","family":"Xue","sequence":"additional","affiliation":[{"name":"Anhui Key Laboratory of Polarization Imaging Detection Technology, Army Artillery and Air Defense Academy of PLA, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7591-943X","authenticated-orcid":false,"given":"Guanglin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Army Artillery and Air Defense Academy of PLA, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3423-1539","authenticated-orcid":false,"given":"Bineng","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Guangxi Normal University, Guilin, China"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref58","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal loss for dense object detection","volume":"42","author":"lin","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref52","first-page":"1","article-title":"Objects as points","author":"zhou","year":"2019","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref16","first-page":"387","article-title":"Improving one-stage visual grounding by recursive subquery construction","volume":"2020","author":"yang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859880"},{"key":"ref18","article-title":"TransVG++: End-to-end visual grounding with language conditioned vision transformer","author":"deng","year":"2022","journal-title":"arXiv 2206 06619"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref50","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref46","article-title":"TAP: Text-aware pre-training for text-VQA and text-caption","author":"yang","year":"2020","journal-title":"arXiv 2012 04638"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"ref47","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3175029"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref43","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref49","first-page":"13041","article-title":"Unified vision-language pretraining for image captioning and VQA","author":"zhou","year":"2020","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3314577"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3269117"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3126591"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2019.2958580"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2019.2927547"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3268455"},{"key":"ref35","article-title":"Combined scaling for zero-shot transfer learning","author":"pham","year":"2021","journal-title":"arXiv 2111 10050"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref37","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref36","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475313"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref32","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"gu","year":"2021","journal-title":"arXiv 2104 13921"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3224525"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.3027926"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3189630"},{"key":"ref38","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3587251"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.520"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref64","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"chen","year":"2018","journal-title":"arXiv 1812 03426"},{"key":"ref20","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"yu","year":"2022","journal-title":"arXiv 2205 01917"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref22","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"jia","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_35"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12343"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref60","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"},{"key":"ref62","first-page":"451","article-title":"PIRC Net: Using proposal indexing, relationships and context for phrase grounding","author":"kovvuri","year":"2018","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_16"}],"container-title":["IEEE Transactions on Instrumentation and Measurement"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/19\/10012124\/10285487.pdf?arnumber=10285487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T19:55:31Z","timestamp":1702324531000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10285487\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tim.2023.3324362","relation":{},"ISSN":["0018-9456","1557-9662"],"issn-type":[{"value":"0018-9456","type":"print"},{"value":"1557-9662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}