{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:54:53Z","timestamp":1781585693128,"version":"3.54.5"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":["61573363"],"award-info":[{"award-number":["61573363"]}],"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":["61832017"],"award-info":[{"award-number":["61832017"]}],"id":[{"id":"10.13039\/501100001809","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":[[2020]]},"DOI":"10.1109\/tpami.2019.2926266","type":"journal-article","created":{"date-parts":[[2019,7,7]],"date-time":"2019-07-07T17:10:37Z","timestamp":1562519437000},"page":"1-1","source":"Crossref","is-referenced-by-count":14,"title":["Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions"],"prefix":"10.1109","author":[{"given":"Yulei","family":"Niu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwu","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shih-Fu","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref31","first-page":"1174","article-title":"Generating expressions that refer to visible objects","author":"mitchell","year":"2013","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Human Language Technol"},{"key":"ref30","first-page":"95","article-title":"Natural reference to objects in a visual domain","author":"mitchell","year":"2010","journal-title":"Proc 6th Int Natural Language Generation Conf"},{"key":"ref37","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref34","first-page":"1946","article-title":"Phrase localization and visual relationship detection with comprehensive linguistic cues","author":"plummer","year":"2017","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/492"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_26"},{"key":"ref28","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"arXiv preprint arXiv 1312 6114"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref2","article-title":"Adversarial autoencoders","author":"makhzani","year":"2015","journal-title":"arXiv preprint arXiv 1511 00613"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00640"},{"key":"ref22","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.766"},{"key":"ref24","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.520"},{"key":"ref26","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(72)90002-3"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.558"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.454"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_47"},{"key":"ref53","first-page":"91","article-title":"Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks","author":"xue","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref52","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-011-9236-8"},{"key":"ref11","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref12","first-page":"410","article-title":"A game-theoretic approach to generating spatial descriptions","author":"golland","year":"2010","journal-title":"Proc Conf Empirical Methods Natural Language Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref16","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref18","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"arXiv preprint arXiv 1312 6114"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00088"},{"key":"ref4","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"chen","year":"2018","journal-title":"arXiv preprint arXiv 1812 02588"},{"key":"ref3","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/1706269.1706296"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"ref47","first-page":"538","article-title":"The optimal reward baseline for gradient-based reinforcement learning","author":"weaver","year":"2001","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.54"},{"key":"ref41","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","author":"sohn","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2803"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.4324\/9781315842011"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/08753569.pdf?arnumber=8753569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:15Z","timestamp":1652194155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8753569\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2926266","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":[[2020]]}}}