{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T01:23:47Z","timestamp":1768094627203,"version":"3.49.0"},"reference-count":65,"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":[{"name":"National Key Research and Development Program of China","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61721004"],"award-info":[{"award-number":["61721004"]}],"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":["U1803261"],"award-info":[{"award-number":["U1803261"]}],"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":["61976132"],"award-info":[{"award-number":["61976132"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["Z201100006820079"],"award-info":[{"award-number":["Z201100006820079"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research Program of Frontier Sciences CAS","award":["ZDBS-LY-JSC032"],"award-info":[{"award-number":["ZDBS-LY-JSC032"]}]},{"name":"CAS-AIR"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3171090","type":"journal-article","created":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T20:20:31Z","timestamp":1651177231000},"page":"4067-4080","source":"Crossref","is-referenced-by-count":1,"title":["A Reconstruction-Based Visual-Acoustic-Semantic Embedding Method for Speech-Image Retrieval"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9619-4935","authenticated-orcid":false,"given":"Wenlong","family":"Cheng","sequence":"first","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"given":"Wei","family":"Tang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8239-7229","authenticated-orcid":false,"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"given":"Yiwen","family":"Luo","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics (IAIR), Xi’an Jiaotong University (XJTU), Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-8647","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Deep convolutional neural network for image deconvolution","author":"xu","year":"0","journal-title":"Proc Adv Conf Neural Inf Process Syst"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/rs12010084"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2949220"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/PRRS.2018.8486338"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240538"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref11","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Adv Conf Neural Inf Process Syst"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.11.026"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref17","article-title":"Vse : Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref16","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref18","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"0","journal-title":"Proc Adv Conf Neural Inf Process Syst"},{"key":"ref51","first-page":"3781","article-title":"Can active memory replace attention","author":"kaiser","year":"0","journal-title":"Proc Adv Int Conf Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505311"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5338"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2020MUP0003"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107248"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1047"},{"key":"ref7","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"0","journal-title":"Proc Adv Conf Neural Inf Process Syst"},{"key":"ref9","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"0","journal-title":"Proc Adv Conf Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01205-0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-273"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2476658"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2011.6100061"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2007.32"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WCRE.2013.6671293"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1368088.1368151"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.05.008"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","first-page":"283","article-title":"Speeding up requirements management in a product software company: Linking customer wishes to product requirements through linguistic engineering","author":"och dag","year":"0","journal-title":"Proc Int l Conf Requirements Eng"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2351676.2351687"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00587"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00177"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2753232"},{"key":"ref23","first-page":"2940","article-title":"Learning aligned cross-modal representations from weakly aligned data","author":"castrej\u00f3n","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref25","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref64","article-title":"Adam: A. Method for Stochastic Optimization","author":"kingma","year":"2014"},{"key":"ref63","article-title":"Adversarial-metric learning for audio-visual cross-modal matching","author":"zheng","year":"2021","journal-title":"IEEE Trans Multimedia"},{"key":"ref22","article-title":"See, hear, and read: Deep aligned representations","author":"aytar","year":"2017","journal-title":"arXiv 1706 00932"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref28","first-page":"139","article-title":"Collecting image annotations using amazon’s mechanical turk","author":"rashtchian","year":"0","journal-title":"Proc NAACL HLT Workshop"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_62"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00190"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957143"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09765364.pdf?arnumber=9765364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T19:45:52Z","timestamp":1699299952000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9765364\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3171090","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}