{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T05:17:31Z","timestamp":1783142251004,"version":"3.54.6"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013058","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["BF2024060"],"award-info":[{"award-number":["BF2024060"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32371877"],"award-info":[{"award-number":["32371877"]}],"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":["62306142"],"award-info":[{"award-number":["62306142"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019091","name":"Key Research and Development Program of Hunan Province of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019091","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2022YFD220 1005"],"award-info":[{"award-number":["2022YFD220 1005"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.inffus.2026.104454","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:08:37Z","timestamp":1778170117000},"page":"104454","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["DBSegFormer: A dual-branch framework based on multi-scale information fusion for semantic segmentation"],"prefix":"10.1016","volume":"135","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8377-8341","authenticated-orcid":false,"given":"Fenger","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6135-3809","authenticated-orcid":false,"given":"He","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3940-5326","authenticated-orcid":false,"given":"Maocheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0652-066X","authenticated-orcid":false,"given":"Liang","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3213-2820","authenticated-orcid":false,"given":"Liyong","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8793-8610","authenticated-orcid":false,"given":"Qiaolin","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104454_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102830","article-title":"Advancing perturbation space expansion based on information fusion for semi-supervised remote sensing image semantic segmentation","volume":"117","author":"Zhou","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104454_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103150","article-title":"MGF-GCN: multimodal interaction Mamba-aided graph convolutional fusion network for semantic segmentation of remote sensing images","volume":"122","author":"Zhao","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104454_bib0003","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3213","article-title":"The cityscapes dataset for semantic urban scene understanding","author":"Cordts","year":"2016"},{"issue":"12","key":"10.1016\/j.inffus.2026.104454_bib0004","doi-asserted-by":"crossref","first-page":"8258","DOI":"10.1109\/TPAMI.2024.3402232","article-title":"EPMF: efficient perception-aware multi-sensor fusion for 3D semantic segmentation","volume":"46","author":"Tan","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104454_bib0005","first-page":"7281","article-title":"HRFormer: high-resolution vision transformer for dense predict","volume":"34","author":"Yuan","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104454_bib0006","series-title":"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":"6","key":"10.1016\/j.inffus.2026.104454_bib0007","doi-asserted-by":"crossref","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","article-title":"UNet++: a nested U-net architecture for medical image segmentation","volume":"39","author":"Zhou","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"4","key":"10.1016\/j.inffus.2026.104454_bib0008","doi-asserted-by":"crossref","first-page":"3111","DOI":"10.1109\/TPAMI.2025.3529350","article-title":"Condition-invariant semantic segmentation","volume":"47","author":"Sakaridis","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104454_bib0009","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11108","article-title":"RandLA-Net: efficient semantic segmentation of large-scale point clouds","author":"Hu","year":"2020"},{"key":"10.1016\/j.inffus.2026.104454_bib0010","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.compag.2018.02.016","article-title":"Deep learning in agriculture: a survey","volume":"147","author":"Kamilaris","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.inffus.2026.104454_bib0011","series-title":"Proceedings of the IEEE 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.inffus.2026.104454_bib0012","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"10.1016\/j.inffus.2026.104454_bib0013","first-page":"1","article-title":"Multiscale global context network for semantic segmentation of high-resolution remote sensing images","volume":"62","author":"Zeng","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104454_bib0014","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1007\/s11263-023-01875-x","article-title":"SFNet: Faster and accurate semantic segmentation via semantic flow","volume":"132","author":"Li","year":"2024","journal-title":"Int. J. Comput. Vis."},{"issue":"10","key":"10.1016\/j.inffus.2026.104454_bib0015","first-page":"7294","article-title":"Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes","volume":"44","author":"Pan","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104454_bib0016","series-title":"Advances in Neural Information Processing Systems","first-page":"12077","article-title":"SegFormer: simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021"},{"key":"10.1016\/j.inffus.2026.104454_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112019","article-title":"AFPN: alignment feature pyramid network for real-time semantic segmentation","volume":"170","author":"Dong","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.inffus.2026.104454_bib0018","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"7087","article-title":"Ultra-high resolution segmentation via boundary-enhanced patch-merging transformer","volume":"39","author":"Sun","year":"2025"},{"key":"10.1016\/j.inffus.2026.104454_bib0019","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5270","article-title":"Mobile-former: bridging mobilenet and transformer","author":"Chen","year":"2022"},{"key":"10.1016\/j.inffus.2026.104454_bib0020","doi-asserted-by":"crossref","first-page":"29191","DOI":"10.52202\/079017-0920","article-title":"MSPE: Multi-scale patch embedding prompts vision transformers to any resolution","volume":"37","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104454_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102594","article-title":"A multi-modal and multi-stage fusion enhancement network for segmentation based on OCT and OCTA images","volume":"113","author":"Quan","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104454_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101880","article-title":"FTransCNN: fusing transformer and a CNN based on fuzzy logic for uncertain medical image segmentation","volume":"99","author":"Ding","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104454_bib0023","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.media.2019.01.012","article-title":"Attention gated networks: learning to leverage salient regions in medical images","volume":"53","author":"Schlemper","year":"2019","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.inffus.2026.104454_bib0024","doi-asserted-by":"crossref","first-page":"9111","DOI":"10.1109\/TMM.2025.3613165","article-title":"Tackling ambiguity from perspectives of uncertainty inference and affinity diversification for weakly supervised semantic segmentation","volume":"27","author":"Yang","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104454_bib0025","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7475","article-title":"Active boundary loss for semantic segmentation","author":"Zhu","year":"2023"},{"issue":"12","key":"10.1016\/j.inffus.2026.104454_bib0026","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.inffus.2026.104454_bib0027","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2881","article-title":"Pyramid scene parsing network","author":"Zhao","year":"2017"},{"key":"10.1016\/j.inffus.2026.104454_bib0028","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1925","article-title":"RefineNet: multi-path refinement networks for high-resolution semantic segmentation","author":"Lin","year":"2017"},{"issue":"11","key":"10.1016\/j.inffus.2026.104454_bib0029","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.inffus.2026.104454_bib0030","article-title":"TransUNet: transformers make strong encoders for medical image segmentation","volume":"87","author":"Ma","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.inffus.2026.104454_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106669","article-title":"Semantic segmentation using vision transformers: a survey","volume":"126","author":"Thisanke","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.inffus.2026.104454_bib0032","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6881","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective","author":"Zheng","year":"2021"},{"key":"10.1016\/j.inffus.2026.104454_bib0033","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"568","article-title":"Pyramid vision transformer: a versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104454_bib0034","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"7262","article-title":"Segmenter: transformer for semantic segmentation","author":"Strudel","year":"2021"},{"key":"10.1016\/j.inffus.2026.104454_bib0035","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"issue":"2","key":"10.1016\/j.inffus.2026.104454_bib0036","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1007\/s11263-024-02171-y","article-title":"LLMFormer: Large language model for open-vocabulary semantic segmentation","volume":"133","author":"Shi","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.inffus.2026.104454_bib0037","series-title":"International Conference on Medical Image Computing and Computer-assisted Intervention","first-page":"14","article-title":"TransFuse: fusing transformers and cnns for medical image segmentation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104454_bib0038","first-page":"1","article-title":"Transformer and CNN hybrid deep neural network for semantic segmentation of very-high-resolution remote sensing imagery","volume":"60","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104454_bib0039","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"18113","article-title":"CMX: cross-modal fusion for RGB-X semantic segmentation with transformers","author":"Lai","year":"2022"},{"key":"10.1016\/j.inffus.2026.104454_bib0040","doi-asserted-by":"crossref","first-page":"8639","DOI":"10.1109\/TMM.2024.3380255","article-title":"EISNet: aa multi-modal fusion network for semantic segmentation with events and images","volume":"26","author":"Xie","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104454_bib0041","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","article-title":"SegNeXt: rethinking convolutional attention design for semantic segmentation","author":"Guo","year":"2022"},{"key":"10.1016\/j.inffus.2026.104454_bib0042","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12175","article-title":"CMT: convolutional neural networks meet vision transformers","author":"Guo","year":"2022"},{"key":"10.1016\/j.inffus.2026.104454_bib0043","doi-asserted-by":"crossref","first-page":"5458","DOI":"10.1109\/TIP.2025.3599673","article-title":"Enhancing multimodal learning via hierarchical fusion architecture search with inconsistency mitigation","volume":"34","author":"Long","year":"2025","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"10.1016\/j.inffus.2026.104454_bib0044","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1109\/TEVC.2023.3314766","article-title":"Pareto-wise ranking classifier for multiobjective evolutionary neural architecture search","volume":"28","author":"Ma","year":"2023","journal-title":"IEEE Trans. Evol. Comput."},{"key":"10.1016\/j.inffus.2026.104454_bib0045","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.1016\/j.inffus.2026.104454_bib0046","first-page":"6378","article-title":"SCTNet: single-branch CNN with transformer semantic information for real-time segmentation","volume":"38","author":"Xu","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.inffus.2026.104454_bib0047","series-title":"European Conference on Computer Vision","first-page":"92","article-title":"Embedding-free transformer with inference spatial reduction for efficient semantic segmentation","author":"Yu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104454_bib0048","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1290","article-title":"Masked-attention mask transformer for universal image segmentation","author":"Cheng","year":"2022"},{"key":"10.1016\/j.inffus.2026.104454_bib0049","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"1314","article-title":"Searching for MobileNetV3","author":"Howard","year":"2019"},{"key":"10.1016\/j.inffus.2026.104454_bib0050","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19529","article-title":"PIDNet: a real-time semantic segmentation network inspired by PID controllers","author":"Xu","year":"2023"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003349?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003349?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T04:46:35Z","timestamp":1783140395000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526003349"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":50,"alternative-id":["S1566253526003349"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104454","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DBSegFormer: A dual-branch framework based on multi-scale information fusion for semantic segmentation","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104454","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104454"}}