{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T11:34:06Z","timestamp":1774179246955,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0118802"],"award-info":[{"award-number":["2022ZD0118802"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2064"],"award-info":[{"award-number":["U20B2064"]}],"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":["62102181"],"award-info":[{"award-number":["62102181"]}],"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":["62322211"],"award-info":[{"award-number":["62322211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Youth Innovation Promotion Association of CAS","award":["2020108"],"award-info":[{"award-number":["2020108"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tpami.2023.3339628","type":"journal-article","created":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T18:21:12Z","timestamp":1701800472000},"page":"3213-3229","source":"Crossref","is-referenced-by-count":36,"title":["Context Disentangling and Prototype Inheriting for Robust Visual Grounding"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3414-2421","authenticated-orcid":false,"given":"Wei","family":"Tang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8437-4824","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9612-3707","authenticated-orcid":false,"given":"Xuejing","family":"Liu","sequence":"additional","affiliation":[{"name":"SenseTime Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2964-426X","authenticated-orcid":false,"given":"Lu","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5341-5985","authenticated-orcid":false,"given":"Zechao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01647-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859880"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186410"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1349"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2624140"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref14","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"Chen","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00427"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413677"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20123"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"ref27","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.4324\/9781032633275-4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1602.001.0001"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01613-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01342-x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2013.15"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref37","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref38","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_9"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3023438"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01384"},{"key":"ref47","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01507"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_9"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16249"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108792"},{"key":"ref54","article-title":"Multimodal open-vocabulary video classification via pre-trained vision and language models","author":"Qian","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413884"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"ref57","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oord"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/SIU49456.2020.9302054"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_16"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10490207\/10342826.pdf?arnumber=10342826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:31:01Z","timestamp":1712691061000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342826\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":72,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3339628","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}