{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:58:12Z","timestamp":1780934292440,"version":"3.54.1"},"reference-count":36,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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.2026.114037","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T23:29:49Z","timestamp":1779492589000},"page":"114037","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Hybrid linear attention: A vision transformer integrating selective sampling softmax and multi-feature fusion enhancement"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3329-0275","authenticated-orcid":false,"given":"Senqi","family":"Guan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxin","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunlong","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linlin","family":"Zong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyue","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianchao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114037_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111332","article-title":"Enhancing textual textbook question answering with large language models and retrieval augmented generation","volume":"162","author":"Alawwad","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114037_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111932","article-title":"Instruction-guided fusion of multi-layer visual features in large vision-language models","volume":"170","author":"Li","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114037_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112122","article-title":"A systematic review of interpretability and explainability for speech emotion features in automatic speech emotion recognition","volume":"171","author":"Jayasinghe","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114037_b4","series-title":"Proceedings of the 39th International Conference on Machine Learning","first-page":"23965","article-title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","volume":"vol. 162","author":"Wortsman","year":"2022"},{"key":"10.1016\/j.patcog.2026.114037_b5","doi-asserted-by":"crossref","unstructured":"Z. Liu, H. Hu, Y. Lin, Z. Yao, Z. Xie, Y. Wei, J. Ning, Y. Cao, Z. Zhang, L. Dong, F. Wei, B. Guo, Swin Transformer V2: Scaling Up Capacity and Resolution, in: International Conference on Computer Vision and Pattern Recognition, CVPR, 2022.","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"10.1016\/j.patcog.2026.114037_b6","doi-asserted-by":"crossref","unstructured":"W. Wang, E. Xie, X. Li, D.-P. Fan, K. Song, D. Liang, T. Lu, P. Luo, L. Shao, Pyramid vision transformer: A versatile backbone for dense prediction without convolutions, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 568\u2013578.","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"10.1016\/j.patcog.2026.114037_b7","doi-asserted-by":"crossref","unstructured":"X. Dong, J. Bao, D. Chen, W. Zhang, N. Yu, L. Yuan, D. Chen, B. Guo, Cswin transformer: A general vision transformer backbone with cross-shaped windows, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 12124\u201312134.","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"10.1016\/j.patcog.2026.114037_b8","doi-asserted-by":"crossref","unstructured":"A. Hassani, S. Walton, J. Li, S. Li, H. Shi, Neighborhood attention transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 6185\u20136194.","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"10.1016\/j.patcog.2026.114037_b9","doi-asserted-by":"crossref","unstructured":"Z. Xia, X. Pan, S. Song, L.E. Li, G. Huang, Vision transformer with deformable attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4794\u20134803.","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"10.1016\/j.patcog.2026.114037_b10","doi-asserted-by":"crossref","unstructured":"L. Zhu, X. Wang, Z. Ke, W. Zhang, R.W. Lau, Biformer: Vision transformer with bi-level routing attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 10323\u201310333.","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"10.1016\/j.patcog.2026.114037_b11","doi-asserted-by":"crossref","unstructured":"C. Zhang, X. Xu, L. Wang, Z. Dai, J. Yang, S2wat: Image style transfer via hierarchical vision transformer using strips window attention, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 7024\u20137032.","DOI":"10.1609\/aaai.v38i7.28529"},{"key":"10.1016\/j.patcog.2026.114037_b12","doi-asserted-by":"crossref","unstructured":"D. Han, T. Ye, Y. Han, Z. Xia, S. Pan, P. Wan, S. Song, G. Huang, Agent attention: On the integration of softmax and linear attention, in: European Conference on Computer Vision, 2024.","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"10.1016\/j.patcog.2026.114037_b13","series-title":"International Conference on Machine Learning","first-page":"5156","article-title":"Transformers are rnns: Fast autoregressive transformers with linear attention","author":"Katharopoulos","year":"2020"},{"key":"10.1016\/j.patcog.2026.114037_b14","doi-asserted-by":"crossref","unstructured":"D. Han, X. Pan, Y. Han, S. Song, G. Huang, Flatten transformer: Vision transformer using focused linear attention, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 5961\u20135971.","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"10.1016\/j.patcog.2026.114037_b15","doi-asserted-by":"crossref","unstructured":"H. Cai, J. Li, M. Hu, C. Gan, S. Han, Efficientvit: Lightweight multi-scale attention for high-resolution dense prediction, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 17302\u201317313.","DOI":"10.1109\/ICCV51070.2023.01587"},{"key":"10.1016\/j.patcog.2026.114037_b16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"issue":"12","key":"10.1016\/j.patcog.2026.114037_b17","doi-asserted-by":"crossref","first-page":"9521","DOI":"10.1109\/TPAMI.2024.3425768","article-title":"TCFormer: Visual recognition via token clustering transformer","volume":"46","author":"Zeng","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114037_b18","article-title":"DSwinIR: Rethinking window-based attention for image restoration","author":"Wu","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114037_b19","doi-asserted-by":"crossref","unstructured":"Y. Li, Y. Fan, X. Xiang, D. Demandolx, R. Ranjan, R. Timofte, L. Van Gool, Efficient and explicit modelling of image hierarchies for image restoration, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18278\u201318289.","DOI":"10.1109\/CVPR52729.2023.01753"},{"issue":"12","key":"10.1016\/j.patcog.2026.114037_b20","doi-asserted-by":"crossref","first-page":"10184","DOI":"10.1109\/TPAMI.2024.3434974","article-title":"Qksan: A quantum kernel self-attention network","volume":"46","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"10.1016\/j.patcog.2026.114037_b21","doi-asserted-by":"crossref","first-page":"13995","DOI":"10.1109\/TNNLS.2024.3504828","article-title":"QSAN: A near-term achievable quantum self-attention network","volume":"36","author":"Shi","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114037_b22","doi-asserted-by":"crossref","unstructured":"M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L.-C. Chen, Mobilenetv2: Inverted residuals and linear bottlenecks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"10.1016\/j.patcog.2026.114037_b23","doi-asserted-by":"crossref","unstructured":"X. Liu, H. Peng, N. Zheng, Y. Yang, H. Hu, Y. Yuan, Efficientvit: Memory efficient vision transformer with cascaded group attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14420\u201314430.","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"10.1016\/j.patcog.2026.114037_b24","series-title":"2025 IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"Effective linear vision transformer via selective sampling softmax and multi-feature enhancement","author":"Zhang","year":"2025"},{"key":"10.1016\/j.patcog.2026.114037_b25","doi-asserted-by":"crossref","unstructured":"Y. Chen, X. Dai, D. Chen, M. Liu, X. Dong, L. Yuan, Z. Liu, Mobile-former: Bridging mobilenet and transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5270\u20135279.","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"10.1016\/j.patcog.2026.114037_b26","doi-asserted-by":"crossref","unstructured":"N. Ma, X. Zhang, H.-T. Zheng, J. Sun, Shufflenet v2: Practical guidelines for efficient cnn architecture design, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 116\u2013131.","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"10.1016\/j.patcog.2026.114037_b27","series-title":"Separable self-attention for mobile vision transformers","author":"Mehta","year":"2022"},{"key":"10.1016\/j.patcog.2026.114037_b28","doi-asserted-by":"crossref","unstructured":"K. Han, Y. Wang, Q. Tian, J. Guo, C. Xu, C. Xu, Ghostnet: More features from cheap operations, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 1580\u20131589.","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"10.1016\/j.patcog.2026.114037_b29","doi-asserted-by":"crossref","unstructured":"B. Zoph, V. Vasudevan, J. Shlens, Q.V. Le, Learning transferable architectures for scalable image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8697\u20138710.","DOI":"10.1109\/CVPR.2018.00907"},{"key":"10.1016\/j.patcog.2026.114037_b30","doi-asserted-by":"crossref","unstructured":"B. Chen, P. Li, C. Li, B. Li, L. Bai, C. Lin, M. Sun, J. Yan, W. Ouyang, Glit: Neural architecture search for global and local image transformer, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 12\u201321.","DOI":"10.1109\/ICCV48922.2021.00008"},{"key":"10.1016\/j.patcog.2026.114037_b31","doi-asserted-by":"crossref","unstructured":"H. He, J. Zhang, Y. Cai, H. Chen, X. Hu, Z. Gan, Y. Wang, C. Wang, Y. Wu, L. Xie, Mobilemamba: Lightweight multi-receptive visual mamba network, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 4497\u20134507.","DOI":"10.1109\/CVPR52734.2025.00424"},{"key":"10.1016\/j.patcog.2026.114037_b32","doi-asserted-by":"crossref","unstructured":"A. Howard, M. Sandler, G. Chu, L.-C. Chen, B. Chen, M. Tan, W. Wang, Y. Zhu, R. Pang, V. Vasudevan, et al., Searching for mobilenetv3, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 1314\u20131324.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"10.1016\/j.patcog.2026.114037_b33","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVI","first-page":"544","article-title":"Single path one-shot neural architecture search with uniform sampling","volume":"Vol. 16","author":"Guo","year":"2020"},{"key":"10.1016\/j.patcog.2026.114037_b34","doi-asserted-by":"crossref","unstructured":"M. Tan, B. Chen, R. Pang, V. Vasudevan, M. Sandler, A. Howard, Q.V. Le, Mnasnet: Platform-aware neural architecture search for mobile, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 2820\u20132828.","DOI":"10.1109\/CVPR.2019.00293"},{"key":"10.1016\/j.patcog.2026.114037_b35","doi-asserted-by":"crossref","unstructured":"X. Chu, B. Zhang, R. Xu, Fairnas: Rethinking evaluation fairness of weight sharing neural architecture search, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 12239\u201312248.","DOI":"10.1109\/ICCV48922.2021.01202"},{"key":"10.1016\/j.patcog.2026.114037_b36","series-title":"Mixconv: Mixed depthwise convolutional kernels","author":"Tan","year":"2019"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326010022?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326010022?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:04:17Z","timestamp":1780931057000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326010022"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":36,"alternative-id":["S0031320326010022"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114037","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":"Hybrid linear attention: A vision transformer integrating selective sampling softmax and multi-feature fusion enhancement","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114037","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":"114037"}}