{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T20:43:46Z","timestamp":1765485826949},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,3]]},"DOI":"10.1109\/wacv.2014.6836053","type":"proceedings-article","created":{"date-parts":[[2014,7,28]],"date-time":"2014-07-28T20:51:07Z","timestamp":1406580667000},"page":"556-563","source":"Crossref","is-referenced-by-count":22,"title":["Multimodal fusion using dynamic hybrid models"],"prefix":"10.1109","author":[{"given":"Mohamed R.","family":"Amer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Behjat","family":"Siddiquie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saad","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajay","family":"Divakaran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harpreet","family":"Sawhney","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","article-title":"Reducing the dimensionality of data with neural networks","author":"salakhutdinov","year":"2006","journal-title":"Science"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1124"},{"key":"18","article-title":"Modeling latent discriminative dynamic of multi-dimensional affective signals","author":"ramirez","year":"2011","journal-title":"ACII"},{"key":"15","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP.2002.5745028","article-title":"Cuave: A new audio-visual database for multimodal human-computer interface research","author":"patterson","year":"2002","journal-title":"ICASSP"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.241"},{"key":"13","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"ICML"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2011515"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/34.982900"},{"key":"12","article-title":"Phone recognition using restricted boltzmann machines","author":"mohamed","year":"2009","journal-title":"ICASSP"},{"key":"21","article-title":"Avec 2011-The first international audio visual emotion challenge","author":"schuller","year":"2011","journal-title":"ACII"},{"journal-title":"UGM Matlab Code for Undirected Graphical Models","year":"2012","author":"schmidt","key":"20"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2013.6607590"},{"key":"23","article-title":"Multimodal learning with deep boltzmann machines","author":"srivastava","year":"2012","journal-title":"NIPS"},{"key":"24","article-title":"The recurrent temporal restricted boltzmann machine","author":"sutskever","year":"2008","journal-title":"NIPS"},{"key":"25","article-title":"Learning multilevel distributed representations for high-dimensional sequences","author":"sutskever","year":"2007","journal-title":"AISTATS"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540157"},{"key":"27","article-title":"Two distributedstate models for generating high-dimentional time series","author":"taylor","year":"2011","journal-title":"JMLR"},{"key":"28","article-title":"Hidden-unit conditional random fields","author":"maaten der l van","year":"2011","journal-title":"AISTATS"},{"key":"29","article-title":"Lipreading with local spatiotemporal descriptors","author":"zhao","year":"2009","journal-title":"Transactions on Multimedia"},{"key":"3","article-title":"High-performance semisupervised learning using discriminatively constrained generative models","author":"druck","year":"2010","journal-title":"ICML"},{"key":"2","article-title":"The challenge of multispeaker lip-reading","author":"cox","year":"2008","journal-title":"AVSPN"},{"key":"10","article-title":"Patch based representation of visual speech","author":"lucey","year":"2006","journal-title":"Proc of the HCSNet Workshop on Use of Vision in Human-computer Interaction"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2026513"},{"key":"5","article-title":"Multiple classifier systems for the classification of audio-visual emotional states","author":"glodek","year":"2011","journal-title":"ACII"},{"key":"4","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2007.70710","article-title":"Semi-supervised learning for a hybrid generative\/discriminative classifier based on the maximum entropy principle","author":"fujino","year":"2008","journal-title":"TPAMI"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390224"},{"key":"8","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2001","journal-title":"ICML"}],"event":{"name":"2014 IEEE Winter Conference on Applications of Computer Vision (WACV)","start":{"date-parts":[[2014,3,24]]},"location":"Steamboat Springs, CO, USA","end":{"date-parts":[[2014,3,26]]}},"container-title":["IEEE Winter Conference on Applications of Computer Vision"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6823792\/6835728\/06836053.pdf?arnumber=6836053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T15:15:20Z","timestamp":1602688520000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6836053"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,3]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/wacv.2014.6836053","relation":{},"subject":[],"published":{"date-parts":[[2014,3]]}}}