{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T09:16:52Z","timestamp":1783156612319,"version":"3.54.6"},"reference-count":54,"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":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","award":["810316"],"award-info":[{"award-number":["810316"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","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":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113818","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T16:35:53Z","timestamp":1777307753000},"page":"113818","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Vision transformer Hook for dense predictions"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1136-2501","authenticated-orcid":false,"given":"Siyuan","family":"Mei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1364-4337","authenticated-orcid":false,"given":"Mareike","family":"Thies","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8587-8894","authenticated-orcid":false,"given":"Yipeng","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4196-0289","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9602-6237","authenticated-orcid":false,"given":"Fuxin","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxuan","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0221-506X","authenticated-orcid":false,"given":"Chengze","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2627-3077","authenticated-orcid":false,"given":"Yixing","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0455-3799","authenticated-orcid":false,"given":"Vincent","family":"Christlein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Maier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113818_b1","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, in: International Conference on Learning Representations."},{"key":"10.1016\/j.patcog.2026.113818_b2","series-title":"International Conference on Machine Learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"10.1016\/j.patcog.2026.113818_b3","unstructured":"A.P. Steiner, A. Kolesnikov, X. Zhai, R. Wightman, J. Uszkoreit, L. Beyer, How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers, Trans. Mach. Learn. Res.."},{"key":"10.1016\/j.patcog.2026.113818_b4","unstructured":"M. Oquab, T. Darcet, T. Moutakanni, H.V. Vo, M. Szafraniec, V. Khalidov, P. Fernandez, D. Haziza, F. Massa, A. El-Nouby, et al., DINOv2: Learning Robust Visual Features without Supervision, Trans. Mach. Learn. Res.."},{"key":"10.1016\/j.patcog.2026.113818_b5","doi-asserted-by":"crossref","unstructured":"K. He, X. Chen, S. Xie, Y. Li, P. Doll\u00e1r, R. Girshick, Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10.1016\/j.patcog.2026.113818_b6","unstructured":"H. Bao, L. Dong, S. Piao, F. Wei, BEiT: BERT Pre-Training of Image Transformers, in: International Conference on Learning Representations."},{"key":"10.1016\/j.patcog.2026.113818_b7","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113818_b8","doi-asserted-by":"crossref","unstructured":"S. Zheng, J. Lu, H. Zhao, X. Zhu, Z. Luo, Y. Wang, Y. Fu, J. Feng, T. Xiang, P.H. Torr, et al., Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 6881\u20136890.","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"10.1016\/j.patcog.2026.113818_b9","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113818_b10","series-title":"European Conference on Computer Vision","first-page":"280","article-title":"Exploring plain vision transformer backbones for object detection","author":"Li","year":"2022"},{"key":"10.1016\/j.patcog.2026.113818_b11","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.2026.113818_b12","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"},{"issue":"3","key":"10.1016\/j.patcog.2026.113818_b13","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","article-title":"Pvt v2: Improved baselines with pyramid vision transformer","volume":"8","author":"Wang","year":"2022","journal-title":"Comput. Vis. Media"},{"key":"10.1016\/j.patcog.2026.113818_b14","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113818_b15","series-title":"Beit v2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022"},{"key":"10.1016\/j.patcog.2026.113818_b16","doi-asserted-by":"crossref","unstructured":"M. Ranzinger, G. Heinrich, J. Kautz, P. Molchanov, AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 12490\u201312500.","DOI":"10.1109\/CVPR52733.2024.01187"},{"key":"10.1016\/j.patcog.2026.113818_b17","unstructured":"Z. Chen, Y. Duan, W. Wang, J. He, T. Lu, J. Dai, Y. Qiao, Vision Transformer Adapter for Dense Predictions, in: The Eleventh International Conference on Learning Representations."},{"key":"10.1016\/j.patcog.2026.113818_b18","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.patcog.2026.113818_b19","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113818_b20","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113818_b21","first-page":"1","article-title":"Exploring the usage of pre-trained features for stereo matching","author":"Zhang","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113818_b22","series-title":"Benchmarking detection transfer learning with vision transformers","author":"Li","year":"2021"},{"key":"10.1016\/j.patcog.2026.113818_b23","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.patcog.2026.113818_b24","series-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"10.1016\/j.patcog.2026.113818_b25","doi-asserted-by":"crossref","unstructured":"Z. Zong, G. Song, Y. Liu, Detrs with collaborative hybrid assignments training, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 6748\u20136758.","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"10.1016\/j.patcog.2026.113818_b26","doi-asserted-by":"crossref","unstructured":"B. Cheng, I. Misra, A.G. Schwing, A. Kirillov, R. Girdhar, Masked-attention mask transformer for universal image segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 1290\u20131299.","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"10.1016\/j.patcog.2026.113818_b27","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113818_b28","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.patcog.2026.113818_b29","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 Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"10.1016\/j.patcog.2026.113818_b30","series-title":"MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark","author":"MMSegmentation Contributors","year":"2020"},{"key":"10.1016\/j.patcog.2026.113818_b31","series-title":"MMDetection: Open MMLab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"10.1016\/j.patcog.2026.113818_b32","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.patcog.2026.113818_b33","series-title":"International Conference on Machine Learning","first-page":"10524","article-title":"On layer normalization in the transformer architecture","author":"Xiong","year":"2020"},{"key":"10.1016\/j.patcog.2026.113818_b34","doi-asserted-by":"crossref","unstructured":"F. Chollet, Xception: Deep learning with depthwise separable convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1251\u20131258.","DOI":"10.1109\/CVPR.2017.195"},{"key":"10.1016\/j.patcog.2026.113818_b35","unstructured":"T. Dao, FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning, in: The Twelfth International Conference on Learning Representations."},{"key":"10.1016\/j.patcog.2026.113818_b36","article-title":"How transferable are features in deep neural networks?","volume":"27","author":"Yosinski","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113818_b37","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","article-title":"Semantic understanding of scenes through the ade20k dataset","volume":"127","author":"Zhou","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113818_b38","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.2026.113818_b39","unstructured":"I. Loshchilov, F. Hutter, Decoupled Weight Decay Regularization, in: International Conference on Learning Representations."},{"key":"10.1016\/j.patcog.2026.113818_b40","doi-asserted-by":"crossref","unstructured":"T. Xiao, Y. Liu, B. Zhou, Y. Jiang, J. Sun, Unified perceptual parsing for scene understanding, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 418\u2013434.","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"10.1016\/j.patcog.2026.113818_b41","doi-asserted-by":"crossref","unstructured":"Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, S. Xie, A convnet for the 2020s, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11976\u201311986.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"10.1016\/j.patcog.2026.113818_b42","doi-asserted-by":"crossref","unstructured":"W. Wang, J. Dai, Z. Chen, Z. Huang, Z. Li, X. Zhu, X. Hu, T. Lu, L. Lu, H. Li, et al., Internimage: Exploring large-scale vision foundation models with deformable convolutions, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14408\u201314419.","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"10.1016\/j.patcog.2026.113818_b43","doi-asserted-by":"crossref","unstructured":"H. Caesar, J. Uijlings, V. Ferrari, Coco-stuff: Thing and stuff classes in context, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 1209\u20131218.","DOI":"10.1109\/CVPR.2018.00132"},{"key":"10.1016\/j.patcog.2026.113818_b44","doi-asserted-by":"crossref","unstructured":"Y. Fang, W. Wang, B. Xie, Q. Sun, L. Wu, X. Wang, T. Huang, X. Wang, Y. Cao, Eva: Exploring the limits of masked visual representation learning at scale, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19358\u201319369.","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"10.1016\/j.patcog.2026.113818_b45","doi-asserted-by":"crossref","unstructured":"W. Wang, H. Bao, L. Dong, J. Bjorck, Z. Peng, Q. Liu, K. Aggarwal, O.K. Mohammed, S. Singhal, S. Som, et al., Image as a foreign language: Beit pretraining for vision and vision-language tasks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19175\u201319186.","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"10.1016\/j.patcog.2026.113818_b46","doi-asserted-by":"crossref","unstructured":"W. Su, X. Zhu, C. Tao, L. Lu, B. Li, G. Huang, Y. Qiao, X. Wang, J. Zhou, J. Dai, Towards all-in-one pre-training via maximizing multi-modal mutual information, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15888\u201315899.","DOI":"10.1109\/CVPR52729.2023.01525"},{"key":"10.1016\/j.patcog.2026.113818_b47","series-title":"One-peace: Exploring one general representation model toward unlimited modalities","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113818_b48","doi-asserted-by":"crossref","unstructured":"K. He, G. Gkioxari, P. Doll\u00e1r, R. Girshick, Mask r-cnn, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"10.1016\/j.patcog.2026.113818_b49","doi-asserted-by":"crossref","unstructured":"Z. Cai, N. Vasconcelos, Cascade r-cnn: Delving into high quality object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6154\u20136162.","DOI":"10.1109\/CVPR.2018.00644"},{"key":"10.1016\/j.patcog.2026.113818_b50","unstructured":"Y. Cai, Y. Zhou, Q. Han, J. Sun, X. Kong, J. Li, X. Zhang, Reversible Column Networks, in: The Eleventh International Conference on Learning Representations."},{"key":"10.1016\/j.patcog.2026.113818_b51","doi-asserted-by":"crossref","unstructured":"H. Yang, J. Gee, J. Shi, Brain Decodes Deep Nets, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 23030\u201323040.","DOI":"10.1109\/CVPR52733.2024.02173"},{"key":"10.1016\/j.patcog.2026.113818_b52","series-title":"Perception encoder: The best visual embeddings are not at the output of the network","author":"Bolya","year":"2025"},{"issue":"8","key":"10.1016\/j.patcog.2026.113818_b53","doi-asserted-by":"crossref","first-page":"5227","DOI":"10.1109\/TPAMI.2024.3362475","article-title":"SpectralGPT: Spectral remote sensing foundation model","volume":"46","author":"Hong","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113818_b54","doi-asserted-by":"crossref","DOI":"10.1016\/j.rse.2023.113856","article-title":"Cross-city matters: A multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networks","volume":"299","author":"Hong","year":"2023","journal-title":"Remote Sens. Environ."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007831?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007831?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:31:26Z","timestamp":1783153886000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326007831"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":54,"alternative-id":["S0031320326007831"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113818","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Vision transformer Hook for dense predictions","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113818","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113818"}}