{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T07:28:04Z","timestamp":1768548484184,"version":"3.49.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["62006222"],"award-info":[{"award-number":["62006222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2020.3034494","type":"journal-article","created":{"date-parts":[[2020,11,3]],"date-time":"2020-11-03T20:48:55Z","timestamp":1604436535000},"page":"220-233","source":"Crossref","is-referenced-by-count":30,"title":["Learning Dual Encoding Model for Adaptive Visual Understanding in Visual Dialogue"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3966-511X","authenticated-orcid":false,"given":"Jing","family":"Yu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5463-7176","authenticated-orcid":false,"given":"Xiaoze","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Zengchang","family":"Qin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0280-2336","authenticated-orcid":false,"given":"Weifeng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yue","family":"Hu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3631-256X","authenticated-orcid":false,"given":"Qi","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00603"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019185"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00639"},{"key":"ref40","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"0","journal-title":"Proc ECCV"},{"key":"ref11","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref13","author":"paivio","year":"1971","journal-title":"Imagery and verbal process"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6769"},{"key":"ref15","first-page":"2953","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"Proc NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708709"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0140-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00776-8_21"},{"key":"ref29","first-page":"4967","article-title":"A simple neural network module for relational reasoning","author":"santoro","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref5","first-page":"2","article-title":"Vse++: Improved visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"Proc BMVC"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00683"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00265"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00684"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00648"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_10"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6248"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01068"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451103"},{"key":"ref24","first-page":"10857","article-title":"Two causal principles for improving visual dialog","author":"qi","year":"2020","journal-title":"Proc CVPR"},{"key":"ref41","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2016","journal-title":"Proc ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01007"},{"key":"ref44","first-page":"314","article-title":"Best of both worlds: Transferring knowledge from discriminative learning to a generative visual dialog model","author":"lu","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1648"},{"key":"ref43","first-page":"3719","article-title":"Visual reference resolution using attention memory for visual dialog","author":"seo","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00214"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09247486.pdf?arnumber=9247486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:13Z","timestamp":1652194213000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9247486\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.3034494","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}