{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T21:52:13Z","timestamp":1785880333304,"version":"3.56.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023\\u202FM743790"],"award-info":[{"award-number":["2023\\u202FM743790"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32572212"],"award-info":[{"award-number":["32572212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers and Electronics in Agriculture"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.compag.2026.112096","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T11:40:36Z","timestamp":1782819636000},"page":"112096","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A unified training framework with masked pixel\u2013semantic reconstruction for agricultural image segmentation"],"prefix":"10.1016","volume":"252","author":[{"given":"Guorun","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yucong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6021-3003","authenticated-orcid":false,"given":"Yuefeng","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenghe","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compag.2026.112096_b0005","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15619","article-title":"Self-supervised learning from images with a joint-embedding predictive architecture","author":"Assran","year":"2023"},{"key":"10.1016\/j.compag.2026.112096_b0010","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F., 2021. BEIT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254, Doi: 10.48550\/arXiv.2106.08254."},{"key":"10.1016\/j.compag.2026.112096_b0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2020.105906","article-title":"DropLeaf: a precision farming smartphone tool for real-time quantification of pesticide application coverage","volume":"180","author":"Brandoli","year":"2021","journal-title":"Comput. Electron. Agric."},{"issue":"4","key":"10.1016\/j.compag.2026.112096_b0020","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.compag.2026.112096_b0025","first-page":"205","article-title":"Swin-UNet: U-Net-like pure transformer for medical image segmentation","author":"Cao","year":"2022","journal-title":"European Conference on Computer Vision"},{"key":"10.1016\/j.compag.2026.112096_b0030","unstructured":"Chen, J., Lu, Y., Yu, Q., et al., 2021. TransUNet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306, Doi: 10.48550\/arXiv.2102.04306."},{"key":"10.1016\/j.compag.2026.112096_b0035","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"10.1016\/j.compag.2026.112096_b0040","first-page":"205","article-title":"Swin-Unet: Unet-like pure transformer for medical image segmentation","author":"Cao","year":"2022","journal-title":"European Conference on Computer Vision"},{"key":"10.1016\/j.compag.2026.112096_b0045","series-title":"European Conference on Computer Vision","first-page":"247","article-title":"Bootstrapped masked autoencoders for vision BERT pretraining","author":"Dong","year":"2022"},{"key":"10.1016\/j.compag.2026.112096_b0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2025.110048","article-title":"Agricultural data privacy and federated learning: a review of challenges and opportunities","volume":"232","author":"Dembani","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.compag.2026.112096_b0055","unstructured":"Food and Agriculture Organization of the United Nations, 2023. The impact of disasters on agriculture and food security: Avoiding and reducing losses through investment in resilience. FAO, https:\/\/openknowledge.fao.org\/handle\/20.500.14283\/cc7900en\/, accessed 2023."},{"key":"10.1016\/j.compag.2026.112096_b0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2023.107854","article-title":"Looking behind occlusions: a study on amodal segmentation for robust on-tree apple fruit size estimation","volume":"209","author":"Gen\u00e9-Mola","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.compag.2026.112096_b0065","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10406","article-title":"Omnimae: Single model masked pretraining on images and videos","author":"Girdhar","year":"2023"},{"key":"10.1016\/j.compag.2026.112096_b0070","doi-asserted-by":"crossref","unstructured":"Gao, P., Ma, T., Li, H., et al., 2022. ConvMAE: Masked convolution meets masked autoencoders. arXiv preprint arXiv:2205.03892, Doi: 10.48550\/arXiv.2205.03892.","DOI":"10.52202\/068431-2582"},{"key":"10.1016\/j.compag.2026.112096_b0075","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"},{"issue":"18","key":"10.1016\/j.compag.2026.112096_b0080","doi-asserted-by":"crossref","first-page":"3645","DOI":"10.3390\/electronics13183645","article-title":"An improved Retinex-based approach based on attention mechanisms for low-light image enhancement","volume":"13","author":"Jiang","year":"2024","journal-title":"Electronics"},{"key":"10.1016\/j.compag.2026.112096_b0085","unstructured":"Koroteev, M. V., 2021. BERT: A review of applications in natural language processing and understanding. arXiv preprint arXiv:2103.11943, Doi: 10.48550\/arXiv.2103.11943."},{"key":"10.1016\/j.compag.2026.112096_b0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2022.107436","article-title":"Impurity monitoring study for corn kernel harvesting based on machine vision and CPU-Net","volume":"202","author":"Liu","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.compag.2026.112096_b0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110140","article-title":"CS-Net: Conv-SimpleFormer network for agricultural image segmentation","volume":"147","author":"Liu","year":"2024","journal-title":"Pattern Recogn."},{"key":"10.1016\/j.compag.2026.112096_b0100","unstructured":"Lee, J., Hwang, E. J., Cho, S., Park, J. C., 2025. PiLaMIM: Toward richer visual representations by integrating pixel and latent masked image modeling. arXiv preprint arXiv:2501.03005."},{"issue":"8","key":"10.1016\/j.compag.2026.112096_b0105","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.1049\/cvi2.12311","article-title":"Real-time semantic segmentation network for crops and weeds based on multi-branch structure","volume":"18","author":"Liu","year":"2024","journal-title":"IET Comput. Vis."},{"key":"10.1016\/j.compag.2026.112096_b0110","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2023.110176","article-title":"A comprehensive survey on design and application of autoencoder in deep learning","volume":"138","author":"Li","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.compag.2026.112096_b0115","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.compag.2026.112096_b0120","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1016\/j.aej.2025.02.035","article-title":"MiM-UNet: an efficient building image segmentation network integrating state space models","volume":"120","author":"Liu","year":"2025","journal-title":"Alex. Eng. J."},{"key":"10.1016\/j.compag.2026.112096_b0125","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., et al., 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193."},{"key":"10.1016\/j.compag.2026.112096_b0130","series-title":"IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"879","article-title":"DeepMIM: deep supervision for masked image modeling","author":"Ren","year":"2025"},{"key":"10.1016\/j.compag.2026.112096_b0135","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"issue":"6","key":"10.1016\/j.compag.2026.112096_b0140","doi-asserted-by":"crossref","first-page":"903","DOI":"10.3390\/agriculture14060903","article-title":"High-precision peach fruit segmentation under adverse conditions using swin transformer","volume":"14","author":"Seo","year":"2024","journal-title":"Agriculture"},{"key":"10.1016\/j.compag.2026.112096_b0145","article-title":"DVAE#: Discrete variational autoencoders with relaxed Boltzmann priors","volume":"31","author":"Vahdat","year":"2018","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.compag.2026.112096_b0150","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2023.108568","article-title":"Interactive image segmentation based field boundary perception method and software for autonomous agricultural machinery path planning","volume":"217","author":"Wang","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.compag.2026.112096_b0155","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"SimMIM: a simple framework for masked image modeling","author":"Xie","year":"2022"},{"key":"10.1016\/j.compag.2026.112096_b0160","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.107037","article-title":"Swin MAE: masked autoencoders for small datasets","volume":"161","author":"Xu","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.compag.2026.112096_b0165","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2022.107206","article-title":"Citrus greening disease recognition algorithm based on classification network using TRL-GAN","volume":"200","author":"Xiao","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.compag.2026.112096_b0170","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. Proces. Syst."},{"key":"10.1016\/j.compag.2026.112096_b0175","first-page":"226","article-title":"Exploring text-enhanced mixture-of-experts for semi-supervised medical image segmentation with composite data","author":"Zeng","year":"2025","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"issue":"6","key":"10.1016\/j.compag.2026.112096_b0180","doi-asserted-by":"crossref","first-page":"3296","DOI":"10.1007\/s11263-024-02328-9","article-title":"Pick: Predict and mask for semi-supervised medical image segmentation","volume":"133","author":"Zeng","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.compag.2026.112096_b0185","article-title":"Segment together: a versatile paradigm for semi-supervised medical image segmentation","author":"Zeng","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.compag.2026.112096_b0190","article-title":"Harnessing text insights with visual alignment for medical image segmentation","author":"Zeng","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.compag.2026.112096_b0195","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2025.110130","article-title":"Diffusion model-based image generative method for quality monitoring of direct grain harvesting","volume":"233","author":"Zhang","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.compag.2026.112096_b0200","unstructured":"Zhou, J., Wei, C., Wang, H., Shen, W., Xie, C., Yuille, A., Kong, T., 2021. iBOT: Image BERT pre-training with online tokenizer. arXiv preprint arXiv:2111.07832."},{"key":"10.1016\/j.compag.2026.112096_b0205","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2023.107967","article-title":"CLA: a self-supervised contrastive learning method for leaf disease identification with domain adaptation","volume":"211","author":"Zhao","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.compag.2026.112096_b0210","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2022.107511","article-title":"Modified U-Net for plant diseased leaf image segmentation","volume":"204","author":"Zhang","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.compag.2026.112096_b0215","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2020.105959","article-title":"Hardness recognition of fruits and vegetables based on tactile array information of manipulator","volume":"181","author":"Zhang","year":"2021","journal-title":"Comput. Electron. Agric."}],"container-title":["Computers and Electronics in Agriculture"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0168169926006915?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0168169926006915?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T21:39:18Z","timestamp":1785879558000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0168169926006915"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":43,"alternative-id":["S0168169926006915"],"URL":"https:\/\/doi.org\/10.1016\/j.compag.2026.112096","relation":{},"ISSN":["0168-1699"],"issn-type":[{"value":"0168-1699","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A unified training framework with masked pixel\u2013semantic reconstruction for agricultural image segmentation","name":"articletitle","label":"Article Title"},{"value":"Computers and Electronics in Agriculture","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compag.2026.112096","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"112096"}}