{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:38:34Z","timestamp":1783438714123,"version":"3.54.6"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61502429"],"award-info":[{"award-number":["61502429"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972357"],"award-info":[{"award-number":["61972357"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LY18F020012"],"award-info":[{"award-number":["LY18F020012"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3109518","type":"journal-article","created":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T16:11:26Z","timestamp":1631117486000},"page":"7790-7802","source":"Crossref","is-referenced-by-count":320,"title":["GMNet: Graded-Feature Multilabel-Learning Network for RGB-Thermal Urban Scene Semantic Segmentation"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3055-2493","authenticated-orcid":false,"given":"Wujie","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinfu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingsheng","family":"Lei","sequence":"additional","affiliation":[{"name":"School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of Information and Communication Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8877-2421","authenticated-orcid":false,"given":"Jenq-Neng","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.533"},{"key":"ref38","first-page":"135","article-title":"Depth-aware CNN for RGB-D segmentation","author":"wang","year":"2018","journal-title":"Proc Eur Comput Vis (ECCV)"},{"key":"ref33","first-page":"1","article-title":"EfficientFCN: Holistically-guided decoding for semantic segmentation","author":"liu","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00114"},{"key":"ref31","article-title":"High-resolution representations for labeling pixels and regions","author":"sun","year":"2019","journal-title":"arXiv 1904 04514"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref37","first-page":"213","article-title":"FuseNet: Incorporating depth into semantic segmentation via fusion-based CNN architecture","author":"hazirbas","year":"2017","journal-title":"Vision Computer"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8297085"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00199"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref29","first-page":"325","article-title":"BiSeNet: Bilateral segmentation network for real-time semantic segmentation","author":"yu","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3042065"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00946"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref21","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref24","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref25","article-title":"ENet: A deep neural network architecture for real-time semantic segmentation","author":"paszke","year":"2016","journal-title":"ArXiv 1606 02147"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SKG.2018.00032"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.79"},{"key":"ref54","first-page":"561","article-title":"Bi-directional cross-modality feature propagation with separation-and-aggregation gate for RGB-D semantic segmentation","author":"chen","year":"2020","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.353"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00464"},{"key":"ref10","article-title":"CCAFNet: Crossflow and cross-scale adaptive fusion network for detecting salient objects in RGB-D images","author":"zhou","year":"2021","journal-title":"IEEE Trans Multimedia"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/TCDS.2021.3051010","article-title":"Deep binocular fixation prediction using a hierarchical multimodal fusion network","author":"zhou","year":"2021","journal-title":"IEEE Trans Cognit Develop Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3351180.3351182"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3025166"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2904733"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2993143"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00330"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105484"},{"key":"ref19","article-title":"CEGFNet: Common extraction and gate fusion network for scene parsing of remote sensing images","author":"zhou","year":"2021","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2910667"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2962685"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2020.107766"},{"key":"ref5","article-title":"MFFENet: Multiscale feature fusion and enhancement network for RGB thermal urban road scene parsing","author":"zhou","year":"2021","journal-title":"IEEE Trans Multimedia"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2957386"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3097393"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref9","article-title":"ECFFNet: Effective and consistent feature fusion network for RGB-T salient object detection","author":"zhou","year":"2021","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00405"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2885062"},{"key":"ref48","first-page":"9441","article-title":"PST900: RGB-thermal calibration, dataset and segmentation network","author":"shivakumar","year":"2020","journal-title":"Proc IEEE Int Conf Robot Automat (ICRA)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3066071"},{"key":"ref42","article-title":"TSNet: Three-stream self-attention network for RGB-D indoor semantic segmentation","author":"zhou","year":"2020","journal-title":"IEEE Intell Syst"},{"key":"ref41","article-title":"RedNet: Residual encoder-decoder network for indoor RGB-D semantic segmentation","author":"jiang","year":"2018","journal-title":"arXiv 1806 01054"},{"key":"ref44","first-page":"561","article-title":"Bi-directional cross-modality feature propagation with separation-and-aggregation gate for RGB-D semantic segmentation","author":"chen","year":"2020","journal-title":"Proc Eur Comput Vis (ECCV)"},{"key":"ref43","article-title":"RFBNet: Deep multimodal networks with residual fusion blocks for RGB-D semantic segmentation","author":"deng","year":"2019","journal-title":"arXiv 1907 00135"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09531449.pdf?arnumber=9531449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:10:16Z","timestamp":1770671416000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9531449\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3109518","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}