{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:26:20Z","timestamp":1772907980307,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2016YFB1001002"],"award-info":[{"award-number":["2016YFB1001002"]}]},{"DOI":"10.13039\/501100002358","name":"Beihang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002358","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tip.2020.2983567","type":"journal-article","created":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T20:58:31Z","timestamp":1585774711000},"page":"5420-5430","source":"Crossref","is-referenced-by-count":40,"title":["STC-GAN: Spatio-Temporally Coupled Generative Adversarial Networks for Predictive Scene Parsing"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6955-6635","authenticated-orcid":false,"given":"Mengshi","family":"Qi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8001-2703","authenticated-orcid":false,"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3497-5052","authenticated-orcid":false,"given":"Annan","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-9729","authenticated-orcid":false,"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126474"},{"key":"ref33","first-page":"2234","article-title":"Improved techniques for training gans","author":"salimans","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"5040","article-title":"Disentangling factors of variation in deep representation using adversarial training","author":"mathieu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","article-title":"Hierarchical long-term video prediction without supervision","author":"wichers","year":"2018","journal-title":"arXiv 1806 04768"},{"key":"ref30","article-title":"Video prediction with appearance and motion conditions","author":"jang","year":"2018","journal-title":"arXiv 1807 02635"},{"key":"ref37","article-title":"Decomposing motion and content for natural video sequence prediction","author":"villegas","year":"2017","journal-title":"arXiv 1706 08033"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","first-page":"802","article-title":"Convolutional lstm network: A machine learning approach for precipitation nowcasting","author":"xingjian","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"469","article-title":"Coupled generative adversarial networks","author":"liu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"ref27","article-title":"Energy-based generative adversarial network","author":"zhao","year":"2016","journal-title":"arXiv 1609 03126"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref2","first-page":"6915","article-title":"Predicting scene parsing and motion dynamics in the future","author":"jin","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.595"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00906"},{"key":"ref22","first-page":"1624","article-title":"Multi-timescale context encoding for scene parsing prediction","author":"chen","year":"2019","journal-title":"Proc IEEE Int Conf Multimedia Expo (ICME)"},{"key":"ref21","first-page":"137","article-title":"Future semantic segmentation with convolutional LSTM","author":"rochan","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref24","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2909053"},{"key":"ref26","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015","journal-title":"arXiv 1511 06434"},{"key":"ref25","first-page":"1486","article-title":"Deep generative image models using a Laplacian pyramid of adversarial networks","author":"denton","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_19"},{"key":"ref51","first-page":"4096","article-title":"Multi-path feedback recurrent neural networks for scene parsing","author":"jin","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"ref55","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref54","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref53","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref52","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref10","article-title":"SegNet: A deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling","author":"badrinarayanan","year":"2015","journal-title":"arXiv 1505 07293"},{"key":"ref11","first-page":"5237","article-title":"KE-GAN: Knowledge embedded generative adversarial networks for semi-supervised scene parsing","author":"qi","year":"2019","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref40","article-title":"FitNets: Hints for thin deep nets","author":"romero","year":"2014","journal-title":"arXiv 1412 6550"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00929"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.477"},{"key":"ref14","first-page":"520","article-title":"Efficient uncertainty estimation for semantic segmentation in videos","author":"huang","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.336"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.345"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00628"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.232"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00686"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.77"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref5","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc Int Conf Med Image Comput Comput Assist Intervent"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.394"},{"key":"ref9","article-title":"Deep multi-scale video prediction beyond mean square error","author":"mathieu","year":"2015","journal-title":"arXiv 1511 05440"},{"key":"ref46","first-page":"519","article-title":"Laplacian pyramid reconstruction and refinement for semantic segmentation","author":"ghiasi","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2708714"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.162"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref44","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015","journal-title":"arXiv 1511 07122"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1093\/beheco\/ark016"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/09052709.pdf?arnumber=9052709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:13Z","timestamp":1651070353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9052709\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.2983567","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}