{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T05:11:53Z","timestamp":1780722713282,"version":"3.54.1"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2018,7,1]],"date-time":"2018-07-01T00:00:00Z","timestamp":1530403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Singapore Ministry of Education Tier 2","award":["ARC28\/14"],"award-info":[{"award-number":["ARC28\/14"]}]},{"name":"Singapore Agency for Science, Technology and Research (A*STAR)"},{"DOI":"10.13039\/501100005049","name":"Science and Engineering Research Council","doi-asserted-by":"crossref","award":["PSF1321202099"],"award-info":[{"award-number":["PSF1321202099"]}],"id":[{"id":"10.13039\/501100005049","id-type":"DOI","asserted-by":"crossref"}]},{"name":"ADSC from A*STAR"},{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Interactive & Digital Media Strategic Research Programme"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/tmm.2017.2774007","type":"journal-article","created":{"date-parts":[[2017,11,15]],"date-time":"2017-11-15T19:23:17Z","timestamp":1510773797000},"page":"1656-1671","source":"Crossref","is-referenced-by-count":29,"title":["Multimodal Recurrent Neural Networks With Information Transfer Layers for Indoor Scene Labeling"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0548-5732","authenticated-orcid":false,"given":"Abrar H.","family":"Abdulnabi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5811-9950","authenticated-orcid":false,"given":"Bing","family":"Shuai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4932-0593","authenticated-orcid":false,"given":"Lap-Pui","family":"Chau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301268"},{"key":"ref70","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383146"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1080"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/28.3-4.321"},{"key":"ref37","first-page":"873","article-title":"Sparse deep belief net\n model for visual area v2","author":"lee","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref36","first-page":"1097","article-title":"ImageNet\n classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref35","first-page":"543","article-title":"Tree-guided group lasso for multi-task regression with structured sparsity","author":"kim","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","first-page":"679","article-title":"Geometry driven semantic labeling of\n indoor scenes","author":"khan","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref60","first-page":"525","article-title":"Histogram of oriented normal vectors for\n object recognition with a depth sensor","author":"tang","year":"0","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2476655"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2006.869625"},{"key":"ref63","first-page":"453","article-title":"Multi-modal unsupervised feature learning for RGB-D scene\n labeling","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.921735"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2455415"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref65","first-page":"1135","article-title":"A new analysis of co-training","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70786"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.86"},{"key":"ref67","article-title":"Canonical correlation analysis","author":"wolfgang","year":"2007","journal-title":"Applied multivariate statistical analysis"},{"key":"ref68","article-title":"A survey on multi-view\n learning","author":"xu","year":"2013"},{"key":"ref69","first-page":"1346","article-title":"Discovering important people and objects for egocentric video summarization","author":"lee","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref2","article-title":"Beyond\n forward shortcuts: Fully convolutional master-slave networks (MSNets) with backward skip connections for semantic\n segmentation","author":"abdulnabi","year":"2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.665"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-4072-6_12"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.79"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0777-6"},{"key":"ref24","first-page":"ii-695","article-title":"Multiscale\n conditional random fields for image labeling","author":"he","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref23","first-page":"25","article-title":"A graph-based framework for multi-task multi-view learning","author":"he","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","article-title":"Gradient flow in recurrent nets:\n the difficulty of learning long-term dependencies","author":"hochreiter","year":"2001","journal-title":"A Field Guide to Dynamical Recurrent Neural Networks"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907236"},{"key":"ref50","first-page":"2759","article-title":"RGB-(D) scene labeling:\n Features and algorithms","author":"ren","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref51","first-page":"101","article-title":"High-level fusion of depth and intensity for pedestrian classification","author":"rohrbach","year":"0","journal-title":"Pattern Recognition - Proc DAGM"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-013-0379-5"},{"key":"ref58","first-page":"2949","article-title":"Multimodal learning with deep Boltzmann\n machines","author":"salakhutdinov","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref57","first-page":"2141","article-title":"Improved\n multimodal deep learning with variation of information","author":"sohn","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref56","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0"},{"key":"ref55","first-page":"746","article-title":"Indoor segmentation and support inference\n from RGBD images","author":"silberman","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130298"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2441781"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(90)90002-E"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.211"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409092"},{"key":"ref13","first-page":"575","article-title":"Scene parsing with multiscale feature\n learning, purity trees, and optimal covers","author":"farabet","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-9038-7"},{"key":"ref16","first-page":"799","article-title":"Bidirectional LSTM networks for improved phoneme classification and recognition","author":"graves","year":"0","journal-title":"Proc Int Conf Artif Neural Netw"},{"key":"ref17","first-page":"549","article-title":"Multi-dimensional recurrent neural networks","author":"graves","year":"0","journal-title":"Proc Int Conf Artif Neural Netw"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639349"},{"key":"ref3","first-page":"iii-1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"0","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549488"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298977"},{"key":"ref8","first-page":"428","article-title":"Human\n detection using oriented histograms of flow and appearance","author":"dalal","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref7","article-title":"Indoor semantic segmentation using depth\n information","author":"couprie","year":"0"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2008.4621195"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6706748"},{"key":"ref45","article-title":"On the\n difficulty of training recurrent neural networks","author":"pascanu","year":"2012"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"ref47","first-page":"-82i","article-title":"Recurrent convolutional neural networks for scene labeling","author":"pinheiro","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482819"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2272636"},{"key":"ref44","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907778"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8386723\/08110684.pdf?arnumber=8110684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T04:03:17Z","timestamp":1643169797000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8110684\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":71,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2017.2774007","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7]]}}}