{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T05:00:26Z","timestamp":1777179626264,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/dicta47822.2019.8945863","type":"proceedings-article","created":{"date-parts":[[2020,1,3]],"date-time":"2020-01-03T00:59:48Z","timestamp":1578013188000},"page":"1-7","source":"Crossref","is-referenced-by-count":41,"title":["Deep Latent Space Learning for Cross-Modal Mapping of Audio and Visual Signals"],"prefix":"10.1109","author":[{"given":"Shah","family":"Nawaz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Kamran","family":"Janjua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ignazio","family":"Gallo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arif","family":"Mahmood","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Calefati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","first-page":"3221","article-title":"Accelerating t-sne using tree-based algorithms","volume":"15","author":"van der maaten","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref30","first-page":"499","article-title":"A discriminative feature learning approach for deep face recognition","author":"wen","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/381066a0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00048-X"},{"key":"ref12","first-page":"123","article-title":"The moving face during speech communication","volume":"2","author":"vatikiotis-bateson","year":"1998","journal-title":"Hearing by Eye II Advances in the Psychology of Speechreading and Auditory-Visual Speech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.1757454"},{"key":"ref14","article-title":"Git loss for deep face recognition","author":"calefati","year":"2018","journal-title":"British Machine Vision Conference"},{"key":"ref15","first-page":"6","article-title":"Deep face recognition","volume":"1","author":"parkhi","year":"2015","journal-title":"BMVC"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref17","first-page":"87","article-title":"Ms-celeb-1m: A dataset and benchmark for large-scale face recognition","author":"guo","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2761539"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-87143-5.50017-2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2004.01.008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref7","first-page":"276","article-title":"On learning associations of faces and voices","author":"kim","year":"2018","journal-title":"Asian Conference on Computer Vision"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2003.09.005"},{"key":"ref9","article-title":"Disjoint mapping network for cross-modal matching of voices and faces","author":"wen","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref20","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.211"},{"key":"ref21","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref26","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2753232"}],"event":{"name":"2019 Digital Image Computing: Techniques and Applications (DICTA)","location":"Perth, Australia","start":{"date-parts":[[2019,12,2]]},"end":{"date-parts":[[2019,12,4]]}},"container-title":["2019 Digital Image Computing: Techniques and Applications (DICTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8943071\/8945805\/08945863.pdf?arnumber=8945863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:15:03Z","timestamp":1657854903000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8945863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/dicta47822.2019.8945863","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}