{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:39:08Z","timestamp":1792791548387,"version":"4.5.0"},"reference-count":37,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004024","name":"Jinan University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004024","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.ins.2026.123948","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T06:09:31Z","timestamp":1785132571000},"page":"123948","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["GSLT: A hierarchical dual-branch framework integrating global semantics and local topology for image recognition"],"prefix":"10.1016","volume":"757","author":[{"given":"Haoyang","family":"Guan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9430-8791","authenticated-orcid":false,"given":"Yuhua","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2026.123948_bib0005","series-title":"ICLR","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.ins.2026.123948_bib0010","series-title":"Advances in Neural Information Processing Systems","first-page":"8291","article-title":"Vision GNN: an image is worth graph of nodes","volume":"35","author":"Han","year":"2022"},{"key":"10.1016\/j.ins.2026.123948_bib0015","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.ins.2026.123948_bib0020","doi-asserted-by":"crossref","first-page":"5746","DOI":"10.1109\/TMM.2025.3542958","article-title":"HGFormer: topology-aware vision transformer with HyperGraph learning","volume":"27","author":"Wang","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.ins.2026.123948_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2024.121406","article-title":"EvolutionViT: multi-objective evolutionary vision transformer pruning under resource constraints","volume":"689","author":"Liu","year":"2025","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2026.123948_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2025.121948","article-title":"Efficient fine-tuning of vision transformer via path-augmented parameter adaptation","volume":"703","author":"Zhou","year":"2025","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2026.123948_bib0035","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"548","article-title":"Pyramid vision transformer: a versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"10.1016\/j.ins.2026.123948_bib0040","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"issue":"1","key":"10.1016\/j.ins.2026.123948_bib0045","first-page":"87","article-title":"Convolution-transformer for image feature extraction","volume":"141","author":"Yin","year":"2024","journal-title":"Comput. Model. Eng. & Sci."},{"key":"10.1016\/j.ins.2026.123948_bib0050","series-title":"Advances in Neural Information Processing Systems","first-page":"13937","article-title":"DynamicViT: efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021"},{"key":"10.1016\/j.ins.2026.123948_bib0055","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"2286","article-title":"ConViT: improving vision transformers with soft convolutional inductive biases","volume":"139","author":"D\u2019Ascoli","year":"2021"},{"key":"10.1016\/j.ins.2026.123948_bib0060","article-title":"Multi-modal remote perception learning for object sensory data","volume":"Volume 18 - 2024","author":"Almujally","year":"2024","journal-title":"Front. Neurorobotics"},{"issue":"1","key":"10.1016\/j.ins.2026.123948_bib0065","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2009","journal-title":"IEEE Trans. Neural Netw."},{"key":"10.1016\/j.ins.2026.123948_bib0070","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"19821","article-title":"Vision HGNN: an image is more than a graph of nodes","author":"Han","year":"2023"},{"key":"10.1016\/j.ins.2026.123948_bib0075","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6118","article-title":"GreedyViG: dynamic axial graph construction for efficient vision GNNs","author":"Munir","year":"2024"},{"issue":"11","key":"10.1016\/j.ins.2026.123948_bib0080","doi-asserted-by":"crossref","first-page":"7397","DOI":"10.1109\/TVCG.2024.3456213","article-title":"Expressive 3D facial animation generation based on local-to-global latent diffusion","volume":"30","author":"Song","year":"2024","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"10.1016\/j.ins.2026.123948_bib0085","first-page":"1","article-title":"S2DBFT: spectral\u2013spatial dual-branch fusion transformer for hyperspectral image classification","volume":"63","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ins.2026.123948_bib0090","author":"Gao"},{"issue":"1","key":"10.1016\/j.ins.2026.123948_bib0095","article-title":"Dual-branch attention network with deep split convolution and multi-dimensional transformers for medical image segmentation","volume":"16","author":"Li","year":"2026","journal-title":"Sci. Rep."},{"key":"10.1016\/j.ins.2026.123948_bib0100","first-page":"1","volume":"62","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"11","key":"10.1016\/j.ins.2026.123948_bib0105","doi-asserted-by":"crossref","first-page":"6607","DOI":"10.1109\/TCYB.2024.3412149","article-title":"Flow2GNN: flexible two-way flow message passing for enhancing GNNs beyond homophily","volume":"54","author":"Huang","year":"2024","journal-title":"IEEE Trans. Cybern."},{"issue":"1","key":"10.1016\/j.ins.2026.123948_bib0110","article-title":"Graph-based vision transformer with sparsity for training on small datasets from scratch","volume":"15","author":"Li","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.ins.2026.123948_bib0115","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2025.111010","article-title":"CT-HiffNet: a contour-texture hierarchical feature fusion network for cropland field parcel extraction from high-resolution remote sensing images","volume":"239","author":"Wu","year":"2025","journal-title":"Comput. Electron. Agric."},{"issue":"1","key":"10.1016\/j.ins.2026.123948_bib0120","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","article-title":"A tutorial on the cross-entropy method","volume":"134","author":"De Boer","year":"2005","journal-title":"Ann. Oper. Res."},{"key":"10.1016\/j.ins.2026.123948_bib0125","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume":"139","author":"Touvron","year":"2021"},{"key":"10.1016\/j.ins.2026.123948_bib0130","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"22","article-title":"CvT: introducing convolutions to vision transformers","author":"Wu","year":"2021"},{"key":"10.1016\/j.ins.2026.123948_bib0135","author":"Yin"},{"key":"10.1016\/j.ins.2026.123948_bib0140","series-title":"Computer Vision \u2013 ECCV 2022","first-page":"516","article-title":"DeiT III: revenge of the ViT","author":"Touvron","year":"2022"},{"key":"10.1016\/j.ins.2026.123948_bib0145","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5641","article-title":"RMT: retentive networks meet vision transformers","author":"Fan","year":"2024"},{"key":"10.1016\/j.ins.2026.123948_bib0150","author":"Xiao"},{"key":"10.1016\/j.ins.2026.123948_bib0155","series-title":"IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium","first-page":"204","article-title":"Introducing eurosat: a novel dataset and deep learning benchmark for land use and land cover classification","author":"Helber","year":"2018"},{"key":"10.1016\/j.ins.2026.123948_bib0160","series-title":"Reading Digits in Natural Images with Unsupervised Feature Learning","author":"Netzer","year":"2011"},{"key":"10.1016\/j.ins.2026.123948_bib0165","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"413","article-title":"Recognizing indoor scenes","author":"Quattoni","year":"2009"},{"key":"10.1016\/j.ins.2026.123948_bib0170","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.neunet.2014.09.005","article-title":"Challenges in representation learning: a report on three machine learning contests","volume":"64","author":"Goodfellow","year":"2015","journal-title":"Neural Netw."},{"key":"10.1016\/j.ins.2026.123948_bib0175","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.ins.2026.123948_bib0180","series-title":"Proceedings of the 37th International Conference on Machine Learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume":"119","author":"Chen","year":"2020"},{"issue":"3","key":"10.1016\/j.ins.2026.123948_bib0185","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1080\/00031305.1992.10475879","article-title":"An introduction to kernel and nearest-neighbor nonparametric regression","volume":"46","author":"Altman","year":"1992","journal-title":"Am. Stat."}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526008790?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526008790?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:54:42Z","timestamp":1792788882000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025526008790"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":37,"alternative-id":["S0020025526008790"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2026.123948","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"GSLT: A hierarchical dual-branch framework integrating global semantics and local topology for image recognition","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2026.123948","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"123948"}}