{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:54:26Z","timestamp":1778270066416,"version":"3.51.4"},"reference-count":46,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61532018"],"award-info":[{"award-number":["61532018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["L182054"],"award-info":[{"award-number":["L182054"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Program for Special Support of Eminent Professionals and National Program for Support of Top-Notch Young Professionals"},{"DOI":"10.13039\/501100012152","name":"National Postdoctoral Program for Innovative Talents","doi-asserted-by":"publisher","award":["BX201700255"],"award-info":[{"award-number":["BX201700255"]}],"id":[{"id":"10.13039\/501100012152","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2018M631583"],"award-info":[{"award-number":["2018M631583"]}],"id":[{"id":"10.13039\/501100002858","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.2019.2933728","type":"journal-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T20:02:15Z","timestamp":1565726535000},"page":"525-537","source":"Crossref","is-referenced-by-count":46,"title":["Image Representations With Spatial Object-to-Object Relations for RGB-D Scene Recognition"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0895-1076","authenticated-orcid":false,"given":"Xinhang","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1596-4326","authenticated-orcid":false,"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bohan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengpeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0634-6075","authenticated-orcid":false,"given":"Gongwei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/502512.502550"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00188"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref30","first-page":"4271","article-title":"Depth cnns for RGB-D scene recognition: Learning from scratch better than transferring from rgb-cnns","author":"song","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref37","first-page":"1871","article-title":"LIBLINEAR: A library for large linear classification","volume":"9","author":"fan","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.214"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref34","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2015","journal-title":"arXiv 1412 6632"},{"key":"ref10","first-page":"783","article-title":"Semantic clustering for robust fine-grained scene recognition","author":"george","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298916"},{"key":"ref12","first-page":"2811","article-title":"Object based scene representations using Fisher scores of local subspace projections","author":"dixit","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref16","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_14"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_47"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref28","first-page":"656","article-title":"Convolutional-recursive deep learning for 3D object classification","author":"socher","year":"2012","journal-title":"Proc NIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.68"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298974"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_56"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref5","first-page":"1378","article-title":"Object bank: A high-level image representation for scene classification and semantic feature sparsification","author":"li","year":"2010","journal-title":"Proc NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2313111"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0660-x"},{"key":"ref2","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.645"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1167\/7.1.10"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0777-6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.324"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/631"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-8614-1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123300"},{"key":"ref42","first-page":"345","article-title":"Learning rich features from RGB-D images for object detection and segmentation","author":"gupta","year":"2014","journal-title":"Proc ECCV"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref44","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0777-6"},{"key":"ref43","author":"everingham","year":"2007","journal-title":"The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0695-z"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/08796408.pdf?arnumber=8796408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:01Z","timestamp":1651070341000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8796408\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tip.2019.2933728","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}