{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:18:42Z","timestamp":1777735122291,"version":"3.51.4"},"reference-count":73,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.engappai.2026.114362","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T19:26:17Z","timestamp":1774034777000},"page":"114362","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Cosine similarity fusion network for real-time Red-Green-Blue and X-modality semantic segmentation of driving scenes"],"prefix":"10.1016","volume":"174","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2176-4993","authenticated-orcid":false,"given":"Danial","family":"Qashqai","sequence":"first","affiliation":[]},{"given":"Emad","family":"Mousavian","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6266-6607","authenticated-orcid":false,"given":"Shahriar B.","family":"Shokouhi","sequence":"additional","affiliation":[]},{"given":"Sattar","family":"Mirzakuchaki","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"12","key":"10.1016\/j.engappai.2026.114362_bib1","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: a deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.114362_bib2","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10587","article-title":"Keep the balance: a parameter-efficient symmetrical framework for RGB+X semantic segmentation","author":"Cai","year":"2025"},{"key":"10.1016\/j.engappai.2026.114362_bib3","series-title":"Rethinking Atrous Convolution for Semantic Image Segmentation","author":"Chen","year":"2017"},{"key":"10.1016\/j.engappai.2026.114362_bib4","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"801","article-title":"Encoder\u2013decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"issue":"4","key":"10.1016\/j.engappai.2026.114362_bib5","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.114362_bib6","series-title":"Proceedings of the European Conference on Computer Vision","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"},{"key":"10.1016\/j.engappai.2026.114362_bib7","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111218","article-title":"Cross-level interaction fusion network-based RGB-T semantic segmentation for distant targets","volume":"161","author":"Chen","year":"2025","journal-title":"Pattern Recogn."},{"key":"10.1016\/j.engappai.2026.114362_bib8","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3029","article-title":"Locality-sensitive deconvolution networks with gated fusion for RGB-D indoor semantic segmentation","author":"Cheng","year":"2017"},{"key":"10.1016\/j.engappai.2026.114362_bib9","first-page":"17 864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.engappai.2026.114362_bib10","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA","first-page":"3213","article-title":"The cityscapes dataset for semantic urban scene understanding","author":"Cordts","year":"2016"},{"key":"10.1016\/j.engappai.2026.114362_bib11","series-title":"Indoor Semantic Segmentation Using Depth Information","author":"Couprie","year":"2013"},{"key":"10.1016\/j.engappai.2026.114362_bib12","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108820","article-title":"Dual-branch deep cross-modal interaction network for semantic segmentation with thermal images","volume":"135","author":"Dai","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114362_bib13","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.engappai.2026.114362_bib14","series-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"4467","article-title":"FEANet: feature-enhanced attention network for RGBthermal real-time semantic segmentation","author":"Deng","year":"2021"},{"key":"10.1016\/j.engappai.2026.114362_bib15","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA","first-page":"9711","article-title":"Rethinking bisenet for real-time semantic segmentation","author":"Fan","year":"2021"},{"key":"10.1016\/j.engappai.2026.114362_bib16","series-title":"Spidermesh: Spatial-Aware demand-guided Recursive Meshing for rgb-t Semantic Segmentation","author":"Fan","year":"2023"},{"key":"10.1016\/j.engappai.2026.114362_bib17","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA","first-page":"3141","article-title":"Dual attention network for scene segmentation","author":"Fu","year":"2019"},{"key":"10.1016\/j.engappai.2026.114362_bib18","doi-asserted-by":"crossref","unstructured":"Gao, S., Yang, X., Jiang, L., Fu, Z. and Du, J., \u201cGlobal feature-based multimodal semantic segmentation,\u201d Pattern Recogn., 151, p.110340, doi: 10.1016\/j.patcog.2024.110340.","DOI":"10.1016\/j.patcog.2024.110340"},{"key":"10.1016\/j.engappai.2026.114362_bib19","series-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"5108","article-title":"MFNet:Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes","author":"Ha","year":"2017"},{"key":"10.1016\/j.engappai.2026.114362_bib20","series-title":"Proceedings of the Asian Conference on Computer Vision","first-page":"213","article-title":"FuseNet: incorporating depth into semantic segmentation via fusion-based CNN architecture","author":"Hazirbas","year":"2016"},{"key":"10.1016\/j.engappai.2026.114362_bib21","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.1016\/j.engappai.2026.114362_bib22","series-title":"Proceedings of the IEEE International Conference on Image Processing","first-page":"1440","article-title":"ACNET: attention based network to exploit complementary features for RGBD semantic segmentation","author":"Hu","year":"2019"},{"key":"10.1016\/j.engappai.2026.114362_bib23","series-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Xi'An, China","first-page":"13656","article-title":"Penet: towards precise and efficient image guided depth completion","author":"Hu","year":"2021"},{"key":"10.1016\/j.engappai.2026.114362_bib24","series-title":"Proceedings of the IEEE International Conference on Image Processing","first-page":"2374","article-title":"Incorporating luminance, depth and color information by a fusion-based network for semantic segmentation","author":"Hung","year":"2019"},{"key":"10.1016\/j.engappai.2026.114362_bib25","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA","first-page":"539","article-title":"Pooling revisited: your receptive field is suboptimal","author":"Jang","year":"2022"},{"key":"10.1016\/j.engappai.2026.114362_bib26","series-title":"Rednet: Residual encoder-decoder Network for Indoor rgb-d Semantic Segmentation","author":"Jiang","year":"2018"},{"key":"10.1016\/j.engappai.2026.114362_bib27","series-title":"Proceedings of the IEEE International Conference on Robotics and Biomimetics (ROBIO)","first-page":"1","article-title":"IGFNet: illumination-guided fusion network for semantic scene understanding using RGB-thermal images","author":"Li","year":"2023"},{"key":"10.1016\/j.engappai.2026.114362_bib28","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127913","article-title":"Residual spatial fusion network for rgb-thermal semantic segmentation","volume":"595","author":"Li","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.engappai.2026.114362_bib29","article-title":"U3M: unbiased multiscale modal fusion model for multimodal semantic segmentation","author":"Li","year":"2025","journal-title":"Pattern Recogn."},{"issue":"7","key":"10.1016\/j.engappai.2026.114362_bib30","doi-asserted-by":"crossref","first-page":"4060","DOI":"10.1109\/LRA.2023.3272269","article-title":"Explicit attention-enhanced fusion for RGB-thermal perception tasks","volume":"8","author":"Liang","year":"2023","journal-title":"IEEE Rob. Autom. Lett."},{"key":"10.1016\/j.engappai.2026.114362_bib31","article-title":"Multi-branch differential bidirectional fusion network for RGB-T semantic segmentation","author":"Liang","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"8","key":"10.1016\/j.engappai.2026.114362_bib32","first-page":"4035","article-title":"Discrimination-aware network pruning for deep model compression","volume":"44","author":"Liu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.114362_bib33","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France","first-page":"8081","article-title":"Multi-interactive feature learning and a full-time multi-modality benchmark for image fusion and segmentation","author":"Liu","year":"2023"},{"key":"10.1016\/j.engappai.2026.114362_bib34","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015"},{"key":"10.1016\/j.engappai.2026.114362_bib35","doi-asserted-by":"crossref","first-page":"6348","DOI":"10.1109\/TMM.2023.3349072","article-title":"Context-aware interaction network for RGB-T semantic segmentation","volume":"26","author":"Lv","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.114362_bib36","first-page":"1","article-title":"A multilevel multimodal fusion transformer for remote sensing semantic segmentation","volume":"62","author":"Ma","year":"2024","journal-title":"IEEE Trans. Geosci. Rem. Sens."},{"key":"10.1016\/j.engappai.2026.114362_bib37","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA","first-page":"12599","article-title":"In defense of pretrained ImageNet architectures for real-time semantic segmentation of road-driving images","author":"Orsic","year":"2019"},{"key":"10.1016\/j.engappai.2026.114362_bib38","series-title":"Pp-liteseg: a Superior real-time Semantic Segmentation Model","author":"Peng","year":"2022"},{"key":"10.1016\/j.engappai.2026.114362_bib39","series-title":"Proceedings of the 5th International Conference on Machine Learning and Computer Application (ICMLCA), Hangzhou, China","first-page":"170","article-title":"RDFormer: efficient RGB-D semantic segmentation in complex outdoor scenes","author":"Peng","year":"2024"},{"key":"10.1016\/j.engappai.2026.114362_bib40","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA","first-page":"724","article-title":"A benchmark dataset and evaluation methodology for video object segmentation","author":"Perazzi","year":"2016"},{"key":"10.1016\/j.engappai.2026.114362_bib41","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1109\/OJSP.2024.3389812","article-title":"MMSFormer: multimodal transformer for material and semantic segmentation","volume":"5","author":"Reza","year":"2024","journal-title":"IEEE Open Journal of Signal Processing"},{"issue":"1","key":"10.1016\/j.engappai.2026.114362_bib42","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1109\/TITS.2017.2750080","article-title":"Erfnet: efficient residual factorized convnet for real-time semantic segmentation","volume":"19","author":"Romera","year":"2018","journal-title":"IEEE Trans. Intell. Transport. Syst."},{"key":"10.1016\/j.engappai.2026.114362_bib43","series-title":"Proceedings of the International Conference on Medical Image Computing and computer-assisted Intervention","first-page":"234","article-title":"U-Net convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"issue":"9","key":"10.1016\/j.engappai.2026.114362_bib44","doi-asserted-by":"crossref","first-page":"14349","DOI":"10.1109\/TITS.2021.3127553","article-title":"FASSD-Net: fast and accurate real-time semantic segmentation for embedded systems","volume":"23","author":"Rosas-Arias","year":"2022","journal-title":"IEEE Trans. Intell. Transport. Syst."},{"key":"10.1016\/j.engappai.2026.114362_bib45","series-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","first-page":"13525","article-title":"Efficient RGB-D semantic segmentation for indoor scene analysis","author":"Seichter","year":"2021"},{"key":"10.1016\/j.engappai.2026.114362_bib46","doi-asserted-by":"crossref","unstructured":"Shen, Z., Wang, J., Weng, Y., Pan, Z., Li, Y. and Wang, J., \u201cECFNet: efficient cross-layer fusion network for real time RGB-thermal urban scene parsing,\u201d Digit. Signal Process., 151, p.104579, doi: 10.1016\/j.dsp.2024.104579.","DOI":"10.1016\/j.dsp.2024.104579"},{"issue":"3","key":"10.1016\/j.engappai.2026.114362_bib47","doi-asserted-by":"crossref","first-page":"2576","DOI":"10.1109\/LRA.2019.2904733","article-title":"RTFNet: RGB-thermal fusion network for semantic segmentation of urban scenes","volume":"4","author":"Sun","year":"2019","journal-title":"IEEE Rob. Autom. Lett."},{"issue":"3","key":"10.1016\/j.engappai.2026.114362_bib48","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.1109\/TASE.2020.2993143","article-title":"FuseSeg: semantic segmentation of urban scenes based on RGB and thermal data fusion","volume":"18","author":"Sun","year":"2021","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.engappai.2026.114362_bib49","series-title":"Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS)","first-page":"1","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.engappai.2026.114362_bib50","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"664","article-title":"Learning common and specific features for RGB-D semantic segmentation with deconvolutional networks","author":"Wang","year":"2016"},{"key":"10.1016\/j.engappai.2026.114362_bib51","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA","first-page":"7794","article-title":"Non-local neural networks","author":"Wang","year":"2018"},{"key":"10.1016\/j.engappai.2026.114362_bib52","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111728","article-title":"Multi-scale frequency attention fusion network for infrared and visible image fusion","volume":"159","author":"Wang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114362_bib53","series-title":"Qdrop: Randomly Dropping Quantization for Extremely low-bit Post-training Quantization","author":"Wei","year":"2022"},{"issue":"4","key":"10.1016\/j.engappai.2026.114362_bib54","doi-asserted-by":"crossref","first-page":"4802","DOI":"10.1364\/OE.416130","article-title":"Polarization-driven semantic segmentation via efficient attention-bridged fusion","volume":"29","author":"Xiang","year":"2021","journal-title":"Opt. Express"},{"key":"10.1016\/j.engappai.2026.114362_bib55","series-title":"Proceedings of the Advances in Neural Information Processing Systems","first-page":"12077","article-title":"SegFormer: simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021"},{"key":"10.1016\/j.engappai.2026.114362_bib56","series-title":"Proceedings of the IEEE International Conference on Robotics and Biomimetics (ROBIO)","first-page":"1129","article-title":"NLFNet: Non-local fusion towards generalized multimodal semantic segmentation across RGB-depth, polarization, and thermal images","author":"Yan","year":"2021"},{"key":"10.1016\/j.engappai.2026.114362_bib57","doi-asserted-by":"crossref","first-page":"151046","DOI":"10.1109\/ACCESS.2024.3478746","article-title":"EFINet: efficient feature interaction network for real-time RGB-D semantic segmentation","volume":"12","author":"Yang","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114362_bib58","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110810","article-title":"Polar edge distance loss in edge-aware plug-and-play scheme for semantic segmentation","volume":"154","author":"Yi","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114362_bib59","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"325","article-title":"Bisenet: bilateral segmentation network for real-time semantic segmentation","author":"Yu","year":"2018"},{"key":"10.1016\/j.engappai.2026.114362_bib60","doi-asserted-by":"crossref","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","article-title":"Bisenet v2: bilateral network with guided aggregation for real-time semantic segmentation","volume":"129","author":"Yu","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.engappai.2026.114362_bib61","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA","first-page":"2633","article-title":"ABMDRNet: Adaptive-weighted bi-directional modality difference reduction network for RGB-T semantic segmentation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.engappai.2026.114362_bib62","series-title":"Attention-Based Dual Supervised Decoder for RGBD Semantic Segmentation","author":"Zhang","year":"2022"},{"issue":"12","key":"10.1016\/j.engappai.2026.114362_bib63","doi-asserted-by":"crossref","first-page":"14679","DOI":"10.1109\/TITS.2023.3300537","article-title":"CMX: Cross-Modal fusion for RGB-X semantic segmentation with transformers","volume":"24","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Intell. Transport. Syst."},{"key":"10.1016\/j.engappai.2026.114362_bib64","doi-asserted-by":"crossref","first-page":"13627","DOI":"10.1007\/s12652-022-03829-6","article-title":"Overview of RGBD semantic segmentation based on deep learning","author":"Zhang","year":"2023","journal-title":"J. Ambient Intell. Hum. Comput."},{"issue":"19","key":"10.1016\/j.engappai.2026.114362_bib65","doi-asserted-by":"crossref","first-page":"23512","DOI":"10.1109\/JSEN.2023.3304637","article-title":"Spatial information-guided adaptive context-aware network for efficient RGB-D semantic segmentation","volume":"23","author":"Zhang","year":"2023","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.engappai.2026.114362_bib66","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada","first-page":"1136","article-title":"Delivering arbitrary-modal semantic segmentation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.engappai.2026.114362_bib67","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.1007\/s12530-024-09567-8","article-title":"Rgb-t semantic segmentation based on cross-operational fusion attention in autonomous driving scenario","volume":"15","author":"Zhang","year":"2024","journal-title":"Evolving Systems"},{"key":"10.1016\/j.engappai.2026.114362_bib68","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA","first-page":"26964","article-title":"Mrfs: mutually reinforcing image fusion and segmentation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.engappai.2026.114362_bib69","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111376","article-title":"Memory-efficient cross-modal attention for RGB-X segmentation and crowd counting","volume":"162","author":"Zhang","year":"2025","journal-title":"Pattern Recogn."},{"key":"10.1016\/j.engappai.2026.114362_bib70","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA","first-page":"6230","article-title":"Pyramid scene parsing network","author":"Zhao","year":"2017"},{"key":"10.1016\/j.engappai.2026.114362_bib71","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA","first-page":"6877","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","author":"Zheng","year":"2021"},{"key":"10.1016\/j.engappai.2026.114362_bib72","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA","first-page":"13062","article-title":"Squeeze-and-attention networks for semantic segmentation","author":"Zhong","year":"2020"},{"issue":"5","key":"10.1016\/j.engappai.2026.114362_bib73","doi-asserted-by":"crossref","first-page":"6477","DOI":"10.1109\/TITS.2025.3528064","article-title":"AGFNet: adaptive gated fusion network for RGB-T semantic segmentation","volume":"26","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Intell. Transport. Syst."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626006433?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626006433?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T22:11:33Z","timestamp":1775945493000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626006433"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":73,"alternative-id":["S0952197626006433"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114362","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Cosine similarity fusion network for real-time Red-Green-Blue and X-modality semantic segmentation of driving scenes","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114362","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114362"}}