{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:48:19Z","timestamp":1791686899536,"version":"4.3.4"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"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","award":["62571205"],"award-info":[{"award-number":["62571205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109514","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T06:52:32Z","timestamp":1787122352000},"page":"109514","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Vision transformers need zoomer: Efficient ViT with categorical attention prior-guided zoom adapter"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7286-337X","authenticated-orcid":false,"given":"Ziwen","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6971-9618","authenticated-orcid":false,"given":"Xiaoyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yushi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5007-3919","authenticated-orcid":false,"given":"Ming","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.neunet.2026.109514_bib0001","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1162\/089892903321662976","article-title":"A cortical mechanism for triggering top-down facilitation in visual object recognition","volume":"15","author":"Bar","year":"2003","journal-title":"Journal of Cognitive Neuroscience"},{"key":"10.1016\/j.neunet.2026.109514_bib0002","unstructured":"Bolya, D., Fu, C.-Y., Dai, X., Zhang, P., Feichtenhofer, C., & Hoffman, J. (2023). Token merging: Your vit but faster. https:\/\/arxiv.org\/abs\/2210.09461."},{"key":"10.1016\/j.neunet.2026.109514_bib0003","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.neunet.2026.109514_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"782","article-title":"Transformer interpretability beyond attention visualization","author":"Chefer","year":"2021"},{"key":"10.1016\/j.neunet.2026.109514_bib0005","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"357","article-title":"Crossvit: Cross-attention multi-scale vision transformer for image classification","author":"Chen","year":"2021"},{"key":"10.1016\/j.neunet.2026.109514_bib0006","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"7042","article-title":"Cf-vit: A general coarse-to-fine method for vision transformer","volume":"vol. 37","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.109514_bib0007","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"17164","article-title":"Diffrate: Differentiable compression rate for efficient vision transformers","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.109514_bib0008","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"},{"issue":"8","key":"10.1016\/j.neunet.2026.109514_bib0009","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.tics.2007.06.010","article-title":"Untangling invariant object recognition","volume":"11","author":"DiCarlo","year":"2007","journal-title":"Trends in Cognitive Sciences"},{"key":"10.1016\/j.neunet.2026.109514_bib0010","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. https:\/\/arxiv.org\/abs\/2010.11929."},{"key":"10.1016\/j.neunet.2026.109514_bib0011","series-title":"European conference on computer vision","first-page":"396","article-title":"Adaptive token sampling for efficient vision transformers","author":"Fayyaz","year":"2022"},{"key":"10.1016\/j.neunet.2026.109514_bib0012","doi-asserted-by":"crossref","first-page":"8291","DOI":"10.52202\/068431-0603","article-title":"Vision gnn: An image is worth graph of nodes","volume":"35","author":"Han","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109514_bib0013","series-title":"International conference on machine learning","first-page":"12633","article-title":"Global context vision transformers","author":"Hatamizadeh","year":"2023"},{"key":"10.1016\/j.neunet.2026.109514_bib0014","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.neunet.2026.109514_bib0015","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"15262","article-title":"Natural adversarial examples","author":"Hendrycks","year":"2021"},{"key":"10.1016\/j.neunet.2026.109514_bib0016","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"22596","article-title":"Towards accurate image coding: Improved autoregressive image generation with dynamic vector quantization","author":"Huang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109514_bib0017","series-title":"International conference on machine learning","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"10.1016\/j.neunet.2026.109514_bib0018","first-page":"18590","article-title":"All tokens matter: Token labeling for training better vision transformers","volume":"34","author":"Jiang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109514_bib0019","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"1383","article-title":"Token fusion: Bridging the gap between token pruning and token merging","author":"Kim","year":"2024"},{"key":"10.1016\/j.neunet.2026.109514_bib0020","series-title":"European conference on computer vision","first-page":"620","article-title":"Spvit: Enabling faster vision transformers via latency-aware soft token pruning","author":"Kong","year":"2022"},{"issue":"1","key":"10.1016\/j.neunet.2026.109514_bib0021","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/S0278-2626(98)91067-3","article-title":"Semantic proximity and shape feature integration effects in visual agnosia for biological kinds","volume":"40","author":"Lecours","year":"1999","journal-title":"Brain and Cognition (Print)"},{"key":"10.1016\/j.neunet.2026.109514_bib0022","doi-asserted-by":"crossref","first-page":"12934","DOI":"10.52202\/068431-0940","article-title":"Efficientformer: Vision transformers at mobilenet speed","volume":"35","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109514_bib0023","unstructured":"Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., & Xie, P. (2022). Not all patches are what you need: Expediting vision transformers via token reorganizations. https:\/\/arxiv.org\/abs\/2202.07800."},{"key":"10.1016\/j.neunet.2026.109514_bib0024","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"},{"key":"10.1016\/j.neunet.2026.109514_bib0025","unstructured":"Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regularization. https:\/\/arxiv.org\/abs\/1711.05101."},{"key":"10.1016\/j.neunet.2026.109514_bib0026","doi-asserted-by":"crossref","first-page":"10068","DOI":"10.52202\/068431-0731","article-title":"Hard imagenet: Segmentations for objects with strong spurious cues","volume":"35","author":"Moayeri","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109514_bib0027","series-title":"Proceedings of the 27th international conference on machine learning (ICML-10)","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"Nair","year":"2010"},{"key":"10.1016\/j.neunet.2026.109514_bib0028","first-page":"24898","article-title":"Ia-red 2: Interpretability-aware redundancy reduction for vision transformers","volume":"34","author":"Pan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109514_bib0029","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"4195","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2023"},{"key":"10.1016\/j.neunet.2026.109514_bib0030","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.neunet.2026.109514_bib0031","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109514_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11987","article-title":"Beyond fixation: Dynamic window visual transformer","author":"Ren","year":"2022"},{"key":"10.1016\/j.neunet.2026.109514_bib0033","series-title":"International conference on machine learning","first-page":"8634","article-title":"Evaluating machine accuracy on imagenet","author":"Shankar","year":"2020"},{"key":"10.1016\/j.neunet.2026.109514_bib0034","first-page":"5770","article-title":"Dynamic grained encoder for vision transformers","volume":"34","author":"Song","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109514_bib0035","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.neunet.2026.109514_bib0036","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12165","article-title":"Patch slimming for efficient vision transformers","author":"Tang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109514_bib0037","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.neunet.2026.109514_bib0038","series-title":"European conference on computer vision","first-page":"516","article-title":"Deit iii: Revenge of the vit","author":"Touvron","year":"2022"},{"key":"10.1016\/j.neunet.2026.109514_bib0039","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"32","article-title":"Going deeper with image transformers","author":"Touvron","year":"2021"},{"key":"10.1016\/j.neunet.2026.109514_bib0040","series-title":"International conference on machine learning","first-page":"9625","article-title":"From imagenet to image classification: contextualizing progress on benchmarks","author":"Tsipras","year":"2020"},{"key":"10.1016\/j.neunet.2026.109514_bib0041","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109514_bib0042","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10375","article-title":"Hard patches mining for masked image modeling","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109514_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109547","article-title":"Aa-trans: Core attention aggregating transformer with information entropy selector for fine-grained visual classification","volume":"140","author":"Wang","year":"2023","journal-title":"Pattern Recognition"},{"issue":"2","key":"10.1016\/j.neunet.2026.109514_bib0044","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1109\/TBME.2014.2356291","article-title":"Exploiting spatial redundancy of image sensor for motion robust rPPG","volume":"62","author":"Wang","year":"2014","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"10.1016\/j.neunet.2026.109514_bib0045","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.neunet.2026.109514_bib0046","first-page":"11960","article-title":"Not all images are worth 16x16 words: Dynamic transformers for efficient image recognition","volume":"34","author":"Wang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109514_bib0047","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2964","article-title":"Evo-vit: Slow-fast token evolution for dynamic vision transformer","volume":"vol. 36","author":"Xu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109514_bib0048","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"558","article-title":"Tokens-to-token vit: Training vision transformers from scratch on imagenet","author":"Yuan","year":"2021"},{"key":"10.1016\/j.neunet.2026.109514_bib0049","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2340","article-title":"Re-labeling imagenet: From single to multi-labels, from global to localized labels","author":"Yun","year":"2021"},{"key":"10.1016\/j.neunet.2026.109514_bib0050","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"16259","article-title":"Point transformer","author":"Zhao","year":"2021"},{"key":"10.1016\/j.neunet.2026.109514_bib0051","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16965","article-title":"Detrs beat yolos on real-time object detection","author":"Zhao","year":"2024"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802600972X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802600972X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:32:42Z","timestamp":1791685962000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089360802600972X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":51,"alternative-id":["S089360802600972X"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109514","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Vision transformers need zoomer: Efficient ViT with categorical attention prior-guided zoom adapter","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109514","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":"109514"}}