{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:04:41Z","timestamp":1760709881914,"version":"3.44.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683540","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"8628-8632","source":"Crossref","is-referenced-by-count":5,"title":["Learning from Multiview Correlations in Open-domain Videos"],"prefix":"10.1109","author":[{"given":"Nils","family":"Holzenberger","sequence":"first","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}]},{"given":"Shruti","family":"Palaskar","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Pranava","family":"Madhyastha","sequence":"additional","affiliation":[{"name":"Imperial College London, UK"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Raman","family":"Arora","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1058"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854050"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2753232"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2619"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1109\/SLT.2018.8639664","article-title":"Acoustic-to-word recognition with sequence-to-sequence models","author":"palaskar","year":"2018"},{"article-title":"Multi-view recurrent neural acoustic word embeddings","year":"2016","author":"he","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1047"},{"article-title":"Objects that sound","year":"2017","author":"arandjelovi?","key":"ref16"},{"article-title":"Unsupervised cross-modal alignment of speech and text embedding spaces","year":"2018","author":"chung","key":"ref17"},{"key":"ref18","first-page":"1083","article-title":"On deep multi-view representation learning","author":"wang","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref19","article-title":"Deep multi-modal representation learning from temporal data","author":"yang","year":"2017","journal-title":"CoRR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/1097-4679(196110)17:4<331::AID-JCLP2270170402>3.0.CO;2-D"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639047"},{"key":"ref27","first-page":"1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"0"},{"key":"ref3","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref6","article-title":"Multimodal machine learning: A survey and taxonomy","author":"baltru\u0161aitis","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"article-title":"Deep gen-eralized canonical correlation analysis","year":"2017","author":"benton","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178840"},{"article-title":"How2: A large-scale dataset for multimodal language understanding","year":"2018","author":"sanabria","key":"ref7"},{"article-title":"Youtube-8m: A large-scale video classification benchmark","year":"2016","author":"abu-el-haija","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462439"},{"key":"ref1","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"article-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"bahdanau","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","first-page":"6546","article-title":"Can spa-tiotemporal 3d cnns retrace the history of 2d cnns and ima-genet?","author":"hara","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2307\/2333955"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"kay","key":"ref25"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, UK","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683540.pdf?arnumber=8683540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:37:49Z","timestamp":1755909469000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683540","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}