{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:23:20Z","timestamp":1775579000749,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2016,7,1]],"date-time":"2016-07-01T00:00:00Z","timestamp":1467331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2016,7]]},"DOI":"10.1109\/tip.2016.2548241","type":"journal-article","created":{"date-parts":[[2016,3,29]],"date-time":"2016-03-29T22:30:02Z","timestamp":1459290602000},"page":"2983-2996","source":"Crossref","is-referenced-by-count":103,"title":["Learning Contextual Dependence With Convolutional Hierarchical Recurrent Neural Networks"],"prefix":"10.1109","volume":"25","author":[{"given":"Zhen","family":"Zuo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Shuai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingxing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yushi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.476"},{"key":"ref71","first-page":"494","article-title":"Mid-level visual element discovery as discriminative mode seeking","author":"doersch","year":"2013","journal-title":"Proc NIPS"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.124"},{"key":"ref39","article-title":"Understanding deep architectures using a recursive convolutional network","author":"eigen","year":"2013"},{"key":"ref38","article-title":"Discriminative recurrent sparse autoencoders","author":"rolfe","year":"2013"},{"key":"ref33","first-page":"899","article-title":"Generalized denoising auto-encoders as generative models","author":"bengio","year":"2013","journal-title":"Proc NIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_15"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref37","first-page":"1","article-title":"Recurrent convolutional neural networks for scene labeling","author":"pinheiro","year":"2014","journal-title":"Proc ICML"},{"key":"ref36","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013"},{"key":"ref35","first-page":"1017","article-title":"Generating text with recurrent neural networks","author":"sutskever","year":"2011","journal-title":"Proc ICML"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref61","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Proc CVPR"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553453"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.186"},{"key":"ref29","first-page":"1339","article-title":"3D object recognition with deep belief nets","author":"nair","year":"2009","journal-title":"Proc NIPS"},{"key":"ref67","first-page":"1378","article-title":"Object bank: A high-level image representation for scene classification & semantic feature sparsification","author":"li","year":"2010","journal-title":"Proc NIPS"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.115"},{"key":"ref69","first-page":"846","article-title":"Max-margin multiple-instance dictionary learning","author":"wang","year":"2013","journal-title":"Proc ICML"},{"key":"ref2","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref1","first-page":"396","article-title":"Handwritten digit recognition with a back-propagation network","author":"le cun","year":"1990","journal-title":"Proc NIPS"},{"key":"ref20","first-page":"1159","article-title":"Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription","author":"boulanger-lewandowski","year":"2012","journal-title":"Proc ICML"},{"key":"ref22","first-page":"1","author":"jaeger","year":"2002","journal-title":"Tutorial on Training Recurrent Neural Networks Covering BPPT RTRL EKF and the ‘Echo State Network’ Approach"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(90)90002-E"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301268"},{"key":"ref23","first-page":"545","article-title":"Offline handwriting recognition with multidimensional recurrent neural networks","author":"graves","year":"2009","journal-title":"Proc NIPS"},{"key":"ref26","first-page":"647","article-title":"DeCAF: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1106"},{"key":"ref51","first-page":"493","article-title":"Hierarchical recurrent neural networks for long-term dependencies","author":"el hihi","year":"1995","journal-title":"Proc NIPS"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref56","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2013"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126286"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2190083"},{"key":"ref52","doi-asserted-by":"crossref","first-page":"2431","DOI":"10.1109\/TCYB.2014.2307862","article-title":"High-order distance-based multiview stochastic learning in image classification","volume":"44","author":"yu","year":"2014","journal-title":"IEEE Trans Cybern"},{"key":"ref10","article-title":"OverFeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2013"},{"key":"ref11","article-title":"DeepID-Net: Multi-stage and deformable deep convolutional neural networks for object detection","author":"ouyang","year":"2014"},{"key":"ref40","article-title":"DRAW: A recurrent neural network for image generation","author":"gregor","year":"2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.244"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref15","article-title":"Statistical language models based on neural networks","author":"mikolov","year":"2012"},{"key":"ref16","article-title":"Training recurrent neural networks","author":"sutskever","year":"2013"},{"key":"ref17","first-page":"1863","article-title":"A clockwork RNN","volume":"32","author":"koutn\u00edk","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref18","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc ICML"},{"key":"ref19","first-page":"1601","article-title":"The recurrent temporal restricted Boltzmann machine","author":"sutskever","year":"2009","journal-title":"Proc NIPS"},{"key":"ref4","first-page":"392","article-title":"Multi-scale orderless pooling of deep convolutional activation features","author":"gong","year":"2014","journal-title":"Proc ECCV"},{"key":"ref3","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Proc NIPS"},{"key":"ref6","article-title":"Going deeper with convolutions","author":"szegedy","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.6"},{"key":"ref8","first-page":"1","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"Proc ECCV"},{"key":"ref7","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref49","first-page":"1110","article-title":"Hierarchical recurrent neural network for skeleton based action recognition","author":"du","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref46","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"venugopalan","year":"2014"},{"key":"ref45","article-title":"Deep visual-semantic alignments for generating image descriptions","author":"karpathy","year":"2014"},{"key":"ref48","article-title":"ReNet: A recurrent neural network based alternative to convolutional networks","author":"visin","year":"2015"},{"key":"ref47","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2014"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.21236\/ADA623249","article-title":"Long-term recurrent convolutional networks for visual recognition and description","author":"donahue","year":"2014"},{"key":"ref41","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc NIPS"},{"key":"ref44","article-title":"Learning a recurrent visual representation for image caption generation","author":"chen","year":"2014"},{"key":"ref43","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/7468583\/07442840.pdf?arnumber=7442840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:43:42Z","timestamp":1642005822000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7442840\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7]]},"references-count":72,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tip.2016.2548241","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7]]}}}