{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T16:19:16Z","timestamp":1762273156237},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T00:00:00Z","timestamp":1701216000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T00:00:00Z","timestamp":1701216000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"International Cooperation in Science and Technology Innovation between Governments","award":["2019YFE0125700"],"award-info":[{"award-number":["2019YFE0125700"]}]},{"name":"the major special project of Anhui Province Science and Technology","award":["2020b06050001"],"award-info":[{"award-number":["2020b06050001"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-17360-z","type":"journal-article","created":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T08:02:45Z","timestamp":1701244965000},"page":"55683-55707","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["EACT-Det: An Efficient Adjusting Criss-cross windows Transformer Embedding Pyramid Networks for Similar Disease Detection"],"prefix":"10.1007","volume":"83","author":[{"given":"Fenmei","family":"Wang","sequence":"first","affiliation":[]},{"given":"Rujing","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Ziliang","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Shifeng","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Xiuzhen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Qiong","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Shijian","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Liu","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,29]]},"reference":[{"key":"17360_CR1","first-page":"22","volume":"2021","author":"H Wu","year":"2021","unstructured":"Wu H et al (2021) CvT: Introducing Convolutions to Vision Transformers. IEEE\/CVF Int Conference Comp Vision (ICCV) 2021:22\u201331","journal-title":"IEEE\/CVF Int Conference Comp Vision (ICCV)"},{"key":"17360_CR2","first-page":"548","volume":"2021","author":"W Wang","year":"2021","unstructured":"Wang W et al (2021) Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions. IEEE\/CVF Int Conference Comp Vision (ICCV) 2021:548\u2013558","journal-title":"IEEE\/CVF Int Conference Comp Vision (ICCV)"},{"key":"17360_CR3","first-page":"12114","volume":"2021","author":"X Dong","year":"2022","unstructured":"Dong X et al (2022) CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows. IEEE\/CVF Conference Comp Vision Pattern Recog (CVPR) 2021:12114\u201312124","journal-title":"IEEE\/CVF Conference Comp Vision Pattern Recog (CVPR)"},{"key":"17360_CR4","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A et al (2021) An image is worth 16x16 Words: Transformers for image recognition at scale. In: International Conference on Learning Representations"},{"key":"17360_CR5","doi-asserted-by":"publisher","unstructured":"Touvron H, Cord M, Douze M et al (2021) Training data-efficient image transformers & distillation through attention. 2020[2023-10-25]. https:\/\/doi.org\/10.48550\/arXiv.2012.12877","DOI":"10.48550\/arXiv.2012.12877"},{"key":"17360_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16342-5","author":"B Karatay","year":"2023","unstructured":"Karatay B, Be\u015ftepe D, Sailunaz K, \u00d6zyer T, Alhajj R (2023) CNN-Transformer based emotion classification from facial expressions and body gestures. Multimed Tools Appl. https:\/\/doi.org\/10.1007\/s11042-023-16342-5","journal-title":"Multimed Tools Appl"},{"key":"17360_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patcog.2017.05.015","volume":"71","author":"SH Lee","year":"2017","unstructured":"Lee SH et al (2017) How deep learning extracts and learns leaf features for plant classification. Pattern Recognit 71:1\u201313","journal-title":"Pattern Recognit"},{"key":"17360_CR8","doi-asserted-by":"publisher","unstructured":"El-Nouby A, Neverova N, Laptev I et al (2021) Training vision transformers for image retrieval[J]. ArXiv2021. https:\/\/doi.org\/10.48550\/arXiv.2102.05644","DOI":"10.48550\/arXiv.2102.05644"},{"key":"17360_CR9","doi-asserted-by":"publisher","unstructured":"Qin Z, Liu J, Zhang X et al (2022) Pyramid fusion transformer for semantic segmentation. https:\/\/doi.org\/10.48550\/arXiv.2201.04019","DOI":"10.48550\/arXiv.2201.04019"},{"key":"17360_CR10","doi-asserted-by":"publisher","unstructured":"Liu J, Wang X (2021) Plant diseases and pests detection based on deep learning: a review. Plant Methods 17. https:\/\/doi.org\/10.1186\/s13007-021-00722-9","DOI":"10.1186\/s13007-021-00722-9"},{"key":"17360_CR11","doi-asserted-by":"publisher","unstructured":"Fuentes A, Yoon S, Park DS (2020) Deep learning-based techniques for plant diseases recognition in real-field scenarios. In: Advanced concepts for intelligent vision systems conference. https:\/\/doi.org\/10.1007\/978-3-030-40605-9_1","DOI":"10.1007\/978-3-030-40605-9_1"},{"key":"17360_CR12","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.compag.2018.01.009","volume":"145","author":"KP Ferentinos","year":"2018","unstructured":"Ferentinos KP (2018) Deep learning models for plant disease detection and diagnosis. Comput Electron Agric 145:311\u2013318","journal-title":"Comput Electron Agric"},{"key":"17360_CR13","doi-asserted-by":"publisher","first-page":"106732","DOI":"10.1016\/j.compag.2022.106732","volume":"193","author":"S Kendler","year":"2022","unstructured":"Kendler S et al (2022) Detection of crop diseases using enhanced variability imagery data and convolutional neural networks. Comput Electron Agric 193:106732","journal-title":"Comput Electron Agric"},{"key":"17360_CR14","doi-asserted-by":"publisher","first-page":"2003","DOI":"10.1016\/j.procs.2020.03.236","volume":"167","author":"S Mishra","year":"2020","unstructured":"Mishra S, Sachan R, Rajpal D (2020) Deep Convolutional Neural Network based Detection System for Real-time Corn Plant Disease Recognition. Procedia Computer Science 167:2003\u20132010","journal-title":"Procedia Computer Science"},{"key":"17360_CR15","unstructured":"Akshitha M et al (2022) Paddy crop disease detection using deep learning techniques. In: 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon), pp 1\u20136 https:\/\/api.semanticscholar.org\/CorpusID:254639857"},{"key":"17360_CR16","doi-asserted-by":"crossref","unstructured":"Zen BP et al (2022) Applications for detecting plant diseases based on artificial intelligence. Sinkron","DOI":"10.33395\/sinkron.v7i4.11833"},{"key":"17360_CR17","first-page":"9992","volume":"2021","author":"Z Liu","year":"2021","unstructured":"Liu Z et al (2021) Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. IEEE\/CVF Int Conference Comp Vision (ICCV) 2021:9992\u201310002","journal-title":"IEEE\/CVF Int Conference Comp Vision (ICCV)"},{"key":"17360_CR18","first-page":"9961","volume":"2021","author":"W Xu","year":"2021","unstructured":"Xu W et al (2021) Co-Scale Conv-Attentional Image Transformers. IEEE\/CVF Int Conference Comp Vision (ICCV) 2021:9961\u20139970","journal-title":"IEEE\/CVF Int Conference Comp Vision (ICCV)"},{"key":"17360_CR19","first-page":"12889","volume":"2021","author":"A Vaswani","year":"2021","unstructured":"Vaswani A et al (2021) Scaling Local Self-Attention for Parameter Efficient Visual Backbones. IEEE\/CVF Conference Comp Vision Pattern Recog (CVPR) 2021:12889\u201312899","journal-title":"IEEE\/CVF Conference Comp Vision Pattern Recog (CVPR)"},{"key":"17360_CR20","first-page":"2978","volume":"2021","author":"P Zhang","year":"2021","unstructured":"Zhang P et al (2021) Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding. IEEE\/CVF Int Conference Comp Vision (ICCV) 2021:2978\u20132988","journal-title":"IEEE\/CVF Int Conference Comp Vision (ICCV)"},{"key":"17360_CR21","first-page":"1922","volume":"44","author":"Z Tian","year":"2020","unstructured":"Tian Z et al (2020) FCOS: A Simple and Strong Anchor-Free Object Detector. IEEE Trans Pattern Anal Mach Intell 44:1922\u20131933","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"17360_CR22","doi-asserted-by":"crossref","unstructured":"He K et al (2015) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"17360_CR23","doi-asserted-by":"publisher","unstructured":"Zhu X et al (2020) Deformable DETR: deformable transformers for end-to-end object detection. ArXiv. https:\/\/doi.org\/10.48550\/arXiv.2010.04159","DOI":"10.48550\/arXiv.2010.04159"},{"key":"17360_CR24","first-page":"14993","volume":"2021","author":"S He","year":"2021","unstructured":"He S et al (2021) TransReID: Transformer-based Object Re-Identification. IEEE\/CVF Int Conference Comp Vision (ICCV) 2021:14993\u201315002","journal-title":"IEEE\/CVF Int Conference Comp Vision (ICCV)"},{"key":"17360_CR25","unstructured":"Jiang Z et al (2021) Token labeling: training a 85.4% top-1 accuracy vision transformer with 56M parameters on ImageNet. ArXiv abs\/2104.10858"},{"key":"17360_CR26","first-page":"538","volume":"2021","author":"L Yuan","year":"2021","unstructured":"Yuan L et al (2021) Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet. IEEE\/CVF Int Conference Comp Vision (ICCV) 2021:538\u2013547","journal-title":"IEEE\/CVF Int Conference Comp Vision (ICCV)"},{"key":"17360_CR27","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1162\/tacl_a_00353","volume":"9","author":"A Roy","year":"2020","unstructured":"Roy A et al (2020) Efficient Content-Based Sparse Attention with Routing Transformers. Transact Ass Computational Linguistics 9:53\u201368","journal-title":"Transact Ass Computational Linguistics"},{"key":"17360_CR28","unstructured":"Tay Y et al (2020) long range arena: a benchmark for efficient transformers. ArXiv abs\/2011.04006"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17360-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-17360-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17360-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T10:28:28Z","timestamp":1715768908000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-17360-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,29]]},"references-count":28,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["17360"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-17360-z","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,29]]},"assertion":[{"value":"27 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 November 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interests"}}]}}