{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:01:03Z","timestamp":1740132063230,"version":"3.37.3"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1724237","CNS-1629700","CCF-1723379","IIS-1718221","IIS-1563727"],"award-info":[{"award-number":["IIS-1724237","CNS-1629700","CCF-1723379","IIS-1718221","IIS-1563727"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Amazon Research Award"},{"name":"AWS ML Research Award"},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,4,1]]},"DOI":"10.1109\/tpami.2020.3029008","type":"journal-article","created":{"date-parts":[[2020,10,6]],"date-time":"2020-10-06T19:49:50Z","timestamp":1602013790000},"page":"2155-2167","source":"Crossref","is-referenced-by-count":9,"title":["Revisiting Image-Language Networks for Open-Ended Phrase Detection"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7074-3219","authenticated-orcid":false,"given":"Bryan A.","family":"Plummer","sequence":"first","affiliation":[{"name":"Department of Computer Science, Boston University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin J.","family":"Shih","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichen","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Boston University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2935-8968","authenticated-orcid":false,"given":"Ke","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Svetlana","family":"Lazebnik","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0711-4313","authenticated-orcid":false,"given":"Stan","family":"Sclaroff","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Boston University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kate","family":"Saenko","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Boston University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3078976"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.95"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_16"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.213"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_42"},{"key":"ref14","first-page":"1909","article-title":"Interpretable and globally optimal prediction for textual grounding using image concepts","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Yeh"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.122"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1281"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2307\/2333955"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"article-title":"Efficient estimation of word representations in vector space","year":"2013","author":"Mikolov","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.507"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref22"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.520"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.320"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11197"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00805"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref39","first-page":"1955","article-title":"VQD: Visual query detection in natural scenes","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Acharya"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00757"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"ref47","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","author":"Andrew"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00438"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"article-title":"The IAPR TC-12 benchmark\u2013A new evaluation resource for visual information systems","year":"2006","author":"Grubinger","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref54","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Xu"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/9729045\/9215037-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9729045\/09215037.pdf?arnumber=9215037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:20:01Z","timestamp":1704846001000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9215037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,1]]},"references-count":54,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3029008","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2022,4,1]]}}}