{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:09:07Z","timestamp":1750306147020,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,10,19]],"date-time":"2017-10-19T00:00:00Z","timestamp":1508371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Institutes of Health of the United States","award":["1R01EB021900"],"award-info":[{"award-number":["1R01EB021900"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation of the United States","doi-asserted-by":"publisher","award":["1738965, 1547428, 1541434, 1440737, 1229213, 1156639"],"award-info":[{"award-number":["1738965, 1547428, 1541434, 1440737, 1229213, 1156639"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,10,19]]},"DOI":"10.1145\/3123266.3123332","type":"proceedings-article","created":{"date-parts":[[2017,10,20]],"date-time":"2017-10-20T13:04:26Z","timestamp":1508504666000},"page":"654-662","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Improved Multimodal Representation Learning with Skip Connections"],"prefix":"10.1145","author":[{"given":"Ning","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Massachusetts Lowell, Lowell, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Cao","sequence":"additional","affiliation":[{"name":"University of Massachusetts Lowell, Lowell, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Massachusetts Lowell, Lowell, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Massachusetts Lowell, Lowell, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,10,19]]},"reference":[{"volume-title":"A kernel method for canonical correlation analysis. arXiv preprint cs\/0609071","year":"2006","author":"Akaho Shotaro","key":"e_1_3_2_1_1_1"},{"key":"e_1_3_2_1_2_1","unstructured":"Galen Andrew Raman Arora Jeff A Bilmes and Karen Livescu. 2013. Deep canonical correlation analysis.. In ICML (3). 1247--1255.   Galen Andrew Raman Arora Jeff A Bilmes and Karen Livescu. 2013. Deep canonical correlation analysis.. In ICML (3). 1247--1255."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639047"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1162\/153244303768966085"},{"volume-title":"How auto-encoders could provide credit assignment in deep networks via target propagation. arXiv preprint arXiv:1407.7906","year":"2014","author":"Bengio Yoshua","key":"e_1_3_2_1_5_1"},{"volume-title":"et almbox","year":"2007","author":"Bengio Yoshua","key":"e_1_3_2_1_6_1"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/2567709.2567749"},{"key":"e_1_3_2_1_8_1","unstructured":"Paramveer Dhillon Dean P Foster and Lyle H Ungar. 2011. Multi-view learning of word embeddings via cca. In Advances in Neural Information Processing Systems. 199--207.   Paramveer Dhillon Dean P Foster and Lyle H Ungar. 2011. Multi-view learning of word embeddings via cca. In Advances in Neural Information Processing Systems. 199--207."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995320"},{"key":"e_1_3_2_1_10_1","unstructured":"Ian Goodfellow Mehdi Mirza Aaron Courville and Yoshua Bengio. 2013. Multi-prediction deep Boltzmann machines. In Advances in Neural Information Processing Systems. 548--556.   Ian Goodfellow Mehdi Mirza Aaron Courville and Yoshua Bengio. 2013. Multi-prediction deep Boltzmann machines. In Advances in Neural Information Processing Systems. 548--556."},{"key":"e_1_3_2_1_11_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems. 2672--2680.   Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems. 2672--2680."},{"volume-title":"MuProp: Unbiased Backpropagation for Stochastic Neural Networks. arXiv preprint arXiv:1511.05176","year":"2015","author":"Gu Shixiang","key":"e_1_3_2_1_12_1"},{"key":"e_1_3_2_1_13_1","volume-title":"AISTATS","volume":"1","author":"Gutmann Michael","year":"2010"},{"volume-title":"Deep Residual Learning for Image Recognition. arXiv preprint arXiv:1512.03385","year":"2015","author":"He Kaiming","key":"e_1_3_2_1_14_1"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"e_1_3_2_1_16_1","unstructured":"Geoffrey E Hinton and Ruslan R Salakhutdinov. 2009. Replicated softmax: an undirected topic model. In Advances in neural information processing systems. 1607--1614.   Geoffrey E Hinton and Ruslan R Salakhutdinov. 2009. Replicated softmax: an undirected topic model. In Advances in neural information processing systems. 1607--1614."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/28.3-4.321"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460104"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/1046920.1088696"},{"volume-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167","year":"2015","author":"Ioffe Sergey","key":"e_1_3_2_1_21_1"},{"volume-title":"Multi-view regression via canonical correlation analysis International Conference on Computational Learning Theory","author":"Kakade Sham M","key":"e_1_3_2_1_22_1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.274"},{"key":"e_1_3_2_1_24_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks Advances in neural information processing systems. 1097--1105.   Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks Advances in neural information processing systems. 1097--1105."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1142\/S012906570000034X"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23528-8_31"},{"volume-title":"Rectified linear units improve restricted boltzmann machines Proceedings of the 27th international conference on machine learning (ICML-10). 807--814","author":"Nair Vinod","key":"e_1_3_2_1_28_1"},{"volume-title":"Proceedings of the 28th international conference on machine learning (ICML-11)","year":"2011","author":"Ngiam Jiquan","key":"e_1_3_2_1_29_1"},{"volume-title":"Variational Bayesian inference with stochastic search. arXiv preprint arXiv:1206.6430","year":"2012","author":"Paisley John","key":"e_1_3_2_1_30_1"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"volume-title":"2010 IEEE Conference on. IEEE, 3408--3415","year":"2010","author":"Putthividhy Duangmanee","key":"e_1_3_2_1_32_1"},{"key":"e_1_3_2_1_33_1","volume-title":"AISTATS","volume":"1","author":"Salakhutdinov Ruslan","year":"2009"},{"key":"e_1_3_2_1_34_1","unstructured":"Kihyuk Sohn Wenling Shang and Honglak Lee. 2014. Improved multimodal deep learning with variation of information Advances in Neural Information Processing Systems. 2141--2149.   Kihyuk Sohn Wenling Shang and Honglak Lee. 2014. Improved multimodal deep learning with variation of information Advances in Neural Information Processing Systems. 2141--2149."},{"key":"e_1_3_2_1_35_1","unstructured":"Nitish Srivastava and Ruslan R Salakhutdinov. 2012. Multimodal learning with deep boltzmann machines. Advances in neural information processing systems. 2222--2230.   Nitish Srivastava and Ruslan R Salakhutdinov. 2012. Multimodal learning with deep boltzmann machines. Advances in neural information processing systems. 2222--2230."},{"key":"e_1_3_2_1_36_1","unstructured":"Nitish Srivastava and Ruslan R Salakhutdinov. 2013. Discriminative transfer learning with tree-based priors Advances in Neural Information Processing Systems. 2094--2102.   Nitish Srivastava and Ruslan R Salakhutdinov. 2013. Discriminative transfer learning with tree-based priors Advances in Neural Information Processing Systems. 2094--2102."},{"key":"e_1_3_2_1_37_1","unstructured":"Rupesh K Srivastava Klaus Greff and J\u00fcrgen Schmidhuber. 2015. Training very deep networks. In Advances in neural information processing systems. 2377--2385.   Rupesh K Srivastava Klaus Greff and J\u00fcrgen Schmidhuber. 2015. Training very deep networks. In Advances in neural information processing systems. 2377--2385."},{"volume-title":"Belongie","year":"2016","author":"Veit Andreas","key":"e_1_3_2_1_38_1"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1743384.1743476"},{"volume-title":"Inferring a semantic representation of text via cross-language correlation analysis NIPS","author":"Vinokourov Alexei","key":"e_1_3_2_1_40_1"},{"key":"e_1_3_2_1_41_1","unstructured":"Weiran Wang Raman Arora Karen Livescu and Jeff A Bilmes. 2015. On Deep Multi-View Representation Learning.. In ICML. 1083--1092.   Weiran Wang Raman Arora Karen Livescu and Jeff A Bilmes. 2015. On Deep Multi-View Representation Learning.. In ICML. 1083--1092."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2476802"},{"volume-title":"Jan Koutn\u00edk, and J\u00fcrgen Schmidhuber.","year":"2016","author":"Zilly Julian Georg","key":"e_1_3_2_1_44_1"}],"event":{"name":"MM '17: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Mountain View California USA","acronym":"MM '17"},"container-title":["Proceedings of the 25th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123332","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3123266.3123332","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3123266.3123332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:39:29Z","timestamp":1750217969000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123332"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,19]]},"references-count":44,"alternative-id":["10.1145\/3123266.3123332","10.1145\/3123266"],"URL":"https:\/\/doi.org\/10.1145\/3123266.3123332","relation":{},"subject":[],"published":{"date-parts":[[2017,10,19]]},"assertion":[{"value":"2017-10-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}