{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T13:24:53Z","timestamp":1787664293394,"version":"build-2736575974"},"reference-count":41,"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\/501100017668","name":"Anhui Provincial Key Research and Development Plan","doi-asserted-by":"publisher","award":["2022k07020006"],"award-info":[{"award-number":["2022k07020006"]}],"id":[{"id":"10.13039\/501100017668","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014934","name":"National Center for Mental Health","doi-asserted-by":"publisher","award":["GXDXK2025A-02"],"award-info":[{"award-number":["GXDXK2025A-02"]}],"id":[{"id":"10.13039\/501100014934","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114355","type":"journal-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T23:01:28Z","timestamp":1783983688000},"page":"114355","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["HGNet: Hypergraph-coordinated multi-scale spatial dependency-aware fusion for image classification"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6688-8077","authenticated-orcid":false,"given":"Xudong","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9923-0062","authenticated-orcid":false,"given":"Nian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9911-1629","authenticated-orcid":false,"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6092-792X","authenticated-orcid":false,"given":"Dian","family":"Jing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114355_b1","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.patcog.2026.114355_b2","first-page":"980","article-title":"Global filter networks for image classification","volume":"34","author":"Rao","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.patcog.2026.114355_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110158","article-title":"Re-abstraction and perturbing support pair network for few-shot fine-grained image classification","volume":"148","author":"Zhang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114355_b4","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.patcog.2026.114355_b5","doi-asserted-by":"crossref","unstructured":"B.H. Ngo, N.-T. Do-Tran, T.-N. Nguyen, H.-G. Jeon, T.J. Choi, Learning CNN on ViT: A hybrid model to explicitly class-specific boundaries for domain adaptation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 28545\u201328554.","DOI":"10.1109\/CVPR52733.2024.02697"},{"key":"10.1016\/j.patcog.2026.114355_b6","doi-asserted-by":"crossref","unstructured":"D. Cai, M. Song, C. Sun, B. Zhang, S. Hong, H. Li, Hypergraph structure learning for hypergraph neural networks, in: Proceedings of the International Joint Conference on Artificial Intelligence, IJCAI, 2022, pp. 1923\u20131929.","DOI":"10.24963\/ijcai.2022\/267"},{"key":"10.1016\/j.patcog.2026.114355_b7","doi-asserted-by":"crossref","first-page":"3301","DOI":"10.1109\/TIP.2024.3391913","article-title":"Multi-view time-series hypergraph neural network for action recognition","volume":"33","author":"Ma","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114355_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103016","article-title":"DHHNN: A dynamic hypergraph hyperbolic neural network based on variational autoencoder for multimodal data integration and node classification","volume":"119","author":"Mei","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.114355_b9","doi-asserted-by":"crossref","unstructured":"C. Xia, X. Wang, F. Lv, X. Hao, Y. Shi, Vit-comer: Vision Transformer with convolutional multi-scale feature interaction for dense predictions, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 5493\u20135502.","DOI":"10.1109\/CVPR52733.2024.00525"},{"key":"10.1016\/j.patcog.2026.114355_b10","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1016\/j.neunet.2023.10.043","article-title":"Multi-scale feature selection network for lightweight image super-resolution","volume":"169","author":"Li","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.patcog.2026.114355_b11","doi-asserted-by":"crossref","unstructured":"S. Hausler, S. Garg, M. Xu, M. Milford, T. Fischer, Patch-netvlad: Multi-scale fusion of locally-global descriptors for place recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 14141\u201314152.","DOI":"10.1109\/CVPR46437.2021.01392"},{"key":"10.1016\/j.patcog.2026.114355_b12","series-title":"International Conference on Machine Learning","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.patcog.2026.114355_b13","doi-asserted-by":"crossref","unstructured":"G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2017, pp. 4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"10.1016\/j.patcog.2026.114355_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.120496","article-title":"MFFCG-Multi feature fusion for hyperspectral image classification using graph attention network","volume":"229","author":"Bhatti","year":"2023","journal-title":"Expert Syst. Appl."},{"issue":"11","key":"10.1016\/j.patcog.2026.114355_b15","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.patcog.2026.114355_b16","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.patcog.2026.114355_b17","doi-asserted-by":"crossref","unstructured":"T. Ridnik, H. Lawen, A. Noy, E. Ben Baruch, G. Sharir, I. Friedman, Tresnet: High performance gpu-dedicated architecture, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 1400\u20131409.","DOI":"10.1109\/WACV48630.2021.00144"},{"key":"10.1016\/j.patcog.2026.114355_b18","doi-asserted-by":"crossref","unstructured":"C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Going deeper with convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10.1016\/j.patcog.2026.114355_b19","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo, Swin Transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.patcog.2026.114355_b20","first-page":"3965","article-title":"Coatnet: Marrying convolution and attention for all data sizes","volume":"34","author":"Dai","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.patcog.2026.114355_b21","article-title":"Robust spatio-temporal graph neural networks with sparse structure learning","volume":"172","author":"Zhang","year":"2026","journal-title":"Pattern Recognit.","ISSN":"https:\/\/id.crossref.org\/issn\/0031-3203","issn-type":"print"},{"key":"10.1016\/j.patcog.2026.114355_b22","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.patcog.2026.114355_b23","series-title":"The World Wide Web Conference","first-page":"972","article-title":"Semi-supervised graph classification: A hierarchical graph perspective","author":"Li","year":"2019"},{"key":"10.1016\/j.patcog.2026.114355_b24","article-title":"A novel hypergraph neural network combining multi-view learning with density awareness","author":"Liao","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114355_b25","doi-asserted-by":"crossref","unstructured":"Y. Feng, H. You, Z. Zhang, R. Ji, Y. Gao, Hypergraph neural networks, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, (01) 2019, pp. 3558\u20133565.","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"10.1016\/j.patcog.2026.114355_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111266","article-title":"Multi-scale hierarchical feature fusion network for change detection","volume":"161","author":"Zheng","year":"2025","journal-title":"Pattern Recognit.","ISSN":"https:\/\/id.crossref.org\/issn\/0031-3203","issn-type":"print"},{"key":"10.1016\/j.patcog.2026.114355_b27","doi-asserted-by":"crossref","unstructured":"T.-Y. Lin, P. Doll\u00e1r, R. Girshick, K. He, B. Hariharan, S. Belongie, Feature pyramid networks for object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"10.1016\/j.patcog.2026.114355_b28","doi-asserted-by":"crossref","unstructured":"C.-F.R. Chen, Q. Fan, R. Panda, CrossViT: Cross-attention multi-scale vision transformer for image classification, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 357\u2013366.","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"10.1016\/j.patcog.2026.114355_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2023.105534","article-title":"HiFuse: Hierarchical multi-scale feature fusion network for medical image classification","volume":"87","author":"Huo","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"issue":"3","key":"10.1016\/j.patcog.2026.114355_b30","first-page":"485","article-title":"Die orthogonalisierung von matrizen","volume":"64","author":"Schmidt","year":"1907","journal-title":"Math. Ann."},{"key":"10.1016\/j.patcog.2026.114355_b31","series-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.patcog.2026.114355_b32","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114355_b33","series-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.patcog.2026.114355_b34","doi-asserted-by":"crossref","unstructured":"M. Yang, D. He, M. Fan, B. Shi, X. Xue, F. Li, E. Ding, J. Huang, Dolg: Single-stage image retrieval with deep orthogonal fusion of local and global features, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 11772\u201311781.","DOI":"10.1109\/ICCV48922.2021.01156"},{"key":"10.1016\/j.patcog.2026.114355_b35","doi-asserted-by":"crossref","unstructured":"Y. Han, P. Wang, S. Kundu, Y. Ding, Z. Wang, Vision hgnn: An image is more than a graph of nodes, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 19878\u201319888.","DOI":"10.1109\/ICCV51070.2023.01820"},{"key":"10.1016\/j.patcog.2026.114355_b36","series-title":"Astroformer: More data might not be all you need for classification","author":"Dagli","year":"2023"},{"issue":"12","key":"10.1016\/j.patcog.2026.114355_b37","doi-asserted-by":"crossref","first-page":"8274","DOI":"10.1109\/TPAMI.2024.3401450","article-title":"Conv2former: A simple transformer-style convnet for visual recognition","volume":"46","author":"Hou","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114355_b38","article-title":"TransXNet: Learning both global and local dynamics with a dual dynamic token mixer for visual recognition","author":"Lou","year":"2025","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114355_b39","series-title":"The caltech-ucsd birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"10.1016\/j.patcog.2026.114355_b40","article-title":"MFID-200: A Multimodal Footprint Dataset and Spatial\u2013Temporal Prompted Transformer for Identification","author":"Zhou","year":"2026","journal-title":"Pattern Recognit."},{"issue":"1","key":"10.1016\/j.patcog.2026.114355_b41","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1038\/s41597-022-01721-8","article-title":"MedMNIST v2-A large-scale lightweight benchmark for 2D and 3D biomedical image classification","volume":"10","author":"Yang","year":"2023","journal-title":"Sci. Data"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013208?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013208?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T13:12:31Z","timestamp":1787663551000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326013208"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":41,"alternative-id":["S0031320326013208"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114355","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"HGNet: Hypergraph-coordinated multi-scale spatial dependency-aware fusion for image classification","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114355","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"114355"}}