{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:34:19Z","timestamp":1774539259413,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972358"],"award-info":[{"award-number":["61972358"]}],"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":["62071427"],"award-info":[{"award-number":["62071427"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY18F020012"],"award-info":[{"award-number":["LY18F020012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3161852","type":"journal-article","created":{"date-parts":[[2022,3,23]],"date-time":"2022-03-23T19:29:40Z","timestamp":1648063780000},"page":"3483-3494","source":"Crossref","is-referenced-by-count":112,"title":["PGDENet: Progressive Guided Fusion and Depth Enhancement Network for RGB-D Indoor Scene Parsing"],"prefix":"10.1109","volume":"25","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"}]},{"given":"Enquan","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, China"}]},{"given":"Jingsheng","family":"Lei","sequence":"additional","affiliation":[{"name":"School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, China"}]},{"given":"Jian","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, China"}]},{"given":"Lu","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of Information and Communication Engineering, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3109518"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00042"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2012.2194474"},{"key":"ref56","article-title":"RFBNet: Deep multimodal networks with residual fusion blocks for rgb-d semantic segmentation","author":"deng","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011327"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00405"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3069297"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3319368"},{"key":"ref53","article-title":"OCNet: Object context network for scene parsing","author":"yuan","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2955101"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2997184"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.79"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3077058"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"ref18","first-page":"1","article-title":"Self-supervised model adaptation for multimodal semantic segmentation","volume":"128","author":"valada","year":"2019","journal-title":"Int J Comput Vis"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_34"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2885062"},{"key":"ref46","first-page":"135","article-title":"Depth-aware cnn for rgb-d segmentation","author":"wang","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6056-8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.147"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.2999462"},{"key":"ref42","article-title":"RedNet: Residual encoder-decoder network for indoor rgb-d semantic segmentation","author":"jiang","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.757"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.161"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049332"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3025166"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2794207"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105484"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00366"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202213"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00533"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00692"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2957915"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2895460"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00068"},{"key":"ref30","first-page":"267","article-title":"Psanet: Point-wise spatial attention network for scene parsing","author":"zhao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428263"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941644"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00927"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2957386"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3080076"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2675166"},{"key":"ref38","article-title":"Indoor semantic segmentation using depth information","author":"couprie","year":"2013"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3086618"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.458"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062689"},{"key":"ref72","article-title":"Efficient rgb-d semantic segmentation for indoor scene analysis","author":"seichter","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3066401"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3077767"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref25","first-page":"5209","article-title":"3D graph neural networks for rgb-d semantic segmentation","author":"qi","year":"2017","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54407-6_33"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00943"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.053"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_5"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3066071"},{"key":"ref21","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"Proc Int Conf Med Image Comput Comput Assist Intervention"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_17"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3050558"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.020"},{"key":"ref60","first-page":"4980","article-title":"RDFNet: Rgb-d multi-level residual feature fusion for indoor semantic segmentation","author":"park","year":"2017","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00322"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2978339"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09740493.pdf?arnumber=9740493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T17:59:52Z","timestamp":1693245592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9740493\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3161852","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}