{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:28:57Z","timestamp":1783542537567,"version":"3.55.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"crossref","award":["2025ZD1603200"],"award-info":[{"award-number":["2025ZD1603200"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Outstanding Youth Science Fund of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52025054"],"award-info":[{"award-number":["52025054"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province of China","doi-asserted-by":"crossref","award":["LH2021E076"],"award-info":[{"award-number":["LH2021E076"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3677060","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T19:50:20Z","timestamp":1774381820000},"page":"9309-9321","source":"Crossref","is-referenced-by-count":1,"title":["DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3148-8286","authenticated-orcid":false,"given":"Yan","family":"Gong","sequence":"first","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8459-9211","authenticated-orcid":false,"given":"Jianli","family":"Lu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1555-8328","authenticated-orcid":false,"given":"Yongsheng","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6086-9387","authenticated-orcid":false,"given":"Jie","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7719-8890","authenticated-orcid":false,"given":"Xiaojuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Fusionopolis, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0831-6934","authenticated-orcid":false,"given":"Susanto","family":"Rahardja","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561675"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3268051"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3143173"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3161852"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103991"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323890"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.104970"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-95465-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2993570"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3160720"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126389"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3613161"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3484490"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382354"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref17","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv:1908.08530"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3313122"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3507536"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3647641"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02760"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610346"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01802"},{"key":"ref27","article-title":"DFormer: Rethinking RGBD representation learning for semantic segmentation","author":"Yin","year":"2023","journal-title":"arXiv:2309.09668"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref29","first-page":"21753","article-title":"Geminifusion: Efficient pixel-wise multimodal fusion for vision transformer","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32970"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/DDCLS66240.2025.11065774"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref37","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Sys. (NIPS)","volume":"34","author":"Xie"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3327377"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681041"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11395-w"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681253"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01622"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130382"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140606"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00756"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113885"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3658114"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3537281"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801872"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.114321"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00176"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111379"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00109"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2025.3575132"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref64","first-page":"9204","article-title":"Pay attention to MLPs","volume-title":"Proc. Conf. Neural Inf. Proces. Syst. (NeurIPS)","author":"Liu"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01188-y"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_28"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/2656106.2656112"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3107672"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2020.3009527"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3056726"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11455264.pdf?arnumber=11455264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:46:19Z","timestamp":1783539979000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11455264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":72,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3677060","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}