{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:25:08Z","timestamp":1730255108913,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956575","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"2539-2545","source":"Crossref","is-referenced-by-count":0,"title":["A hybrid multi-modal visual data cross fusion network for indoor and outdoor scene segmentation"],"prefix":"10.1109","author":[{"given":"Sijie","family":"Hu","sequence":"first","affiliation":[{"name":"Université Paris-Saclay, Univ Evry,IBISC,Evry-Courcouronnes,France,91020"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabien","family":"Bonardi","sequence":"additional","affiliation":[{"name":"Université Paris-Saclay, Univ Evry,IBISC,Evry-Courcouronnes,France,91020"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samia","family":"Bouchafa","sequence":"additional","affiliation":[{"name":"Université Paris-Saclay, Univ Evry,IBISC,Evry-Courcouronnes,France,91020"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Desire","family":"Sidibe","sequence":"additional","affiliation":[{"name":"Université Paris-Saclay, Univ Evry,IBISC,Evry-Courcouronnes,France,91020"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Multi-modal attention-based fusion model for semantic segmentation of rgb-depth images","year":"2019","author":"fooladgar","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.161"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561675"},{"key":"ref36","first-page":"211","article-title":"Imagenet large of International journal computer scale visual recognition challenge","volume":"115","author":"russakovsky","year":"2015","journal-title":"Vision"},{"article-title":"Erfnet: efficient residual factorized convnet for real-time semantic segmentation","year":"2018","author":"romera carmena","key":"ref35"},{"article-title":"Pytorch: An imperative style, high-performance deep learning library","year":"2019","author":"paszke","key":"ref34"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref10"},{"key":"ref11","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","author":"chu","year":"2021","journal-title":"Thirty-Fifth Conference on Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"article-title":"Pvtv2: Improved baselines with pyramid vision transformer","year":"2021","author":"wang","key":"ref13"},{"article-title":"Bitr-unet: a cnn-transformer combined network for mri brain tumor segmentation","year":"2021","author":"jia","key":"ref14"},{"key":"ref15","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"article-title":"Fastformer: Additive attention can be all you need","year":"2021","author":"wu","key":"ref17"},{"key":"ref18","first-page":"746","article-title":"Indoor segmentation and support inference from rgbd images","author":"silberman","year":"2012","journal-title":"European Conference on Computer Vision"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01188-y"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049332"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"ref29","first-page":"213","article-title":"Fusenet: Incorporating depth into semantic segmentation via fusion-based cnn architecture","author":"hazirbas","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"article-title":"Rednet: Residual encoder-decoder network for indoor rgb-d semantic segmentation","year":"2018","author":"jiang","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref2","article-title":"U2fusion: A unified unsupervised image fusion network","author":"xu","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"article-title":"Indoor semantic segmentation using depth information","year":"2013","author":"couprie","key":"ref1"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Fully attentional network for semantic segmentation","year":"2021","author":"song","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"article-title":"Xcit: Cross-covariance image transformers","year":"2021","author":"el-nouby","key":"ref24"},{"article-title":"Segformer: Simple and ef cient design for semantic segmentation with transformers","year":"2021","author":"xie","key":"ref23"},{"key":"ref26","first-page":"555","article-title":"Malleable 2.5 d convolution: Learning receptive fields along the depth-axis for rgb-d scene parsing","author":"xing","year":"2020","journal-title":"Computer Vision–ECCV 2020 16th European Conference Glasgow UK August 23–28 2020 Proceedings Part XIX 16"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.104042"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956575.pdf?arnumber=9956575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:04:14Z","timestamp":1671480254000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956575\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956575","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}