{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T01:06:42Z","timestamp":1780621602434,"version":"3.54.1"},"reference-count":52,"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\/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":["Advanced Engineering Informatics"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.aei.2026.104762","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T12:39:04Z","timestamp":1778071144000},"page":"104762","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["WheatGOAT: Generalizable object-aware tracker via discriminative region semantic learning for wheat ear counting"],"prefix":"10.1016","volume":"74","author":[{"given":"Xingcai","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaoxi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanying","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziang","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G.M.A.D.","family":"Sirishantha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A.S.A.","family":"Salgadoeb","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gefei","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2444-5442","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.aei.2026.104762_b1","doi-asserted-by":"crossref","unstructured":"Z.-Q. Cheng, Q. Dai, H. Li, J. Song, X. Wu, A.G. Hauptmann, Rethinking spatial invariance of convolutional networks for object counting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 19638\u201319648.","DOI":"10.1109\/CVPR52688.2022.01902"},{"key":"10.1016\/j.aei.2026.104762_b2","doi-asserted-by":"crossref","unstructured":"M. Marsden, K. McGuinness, S. Little, C.E. Keogh, N.E. O\u2019Connor, People, penguins and petri dishes: Adapting object counting models to new visual domains and object types without forgetting, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8070\u20138079.","DOI":"10.1109\/CVPR.2018.00842"},{"key":"10.1016\/j.aei.2026.104762_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.116226","article-title":"Towards improved accuracy of UAV-based wheat ears counting: A transfer learning method of the ground-based fully convolutional network","volume":"191","author":"Ma","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.aei.2026.104762_b4","article-title":"Occlusion robust wheat ear counting algorithm based on deep learning","volume":"12","author":"Wang","year":"2021","journal-title":"Front. Plant Sci."},{"key":"10.1016\/j.aei.2026.104762_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2025.110486","article-title":"Early yield estimation in wheat using open access global datasets and artificial intelligence","volume":"237","author":"Akcap\u0131nar","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.aei.2026.104762_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2023.108555","article-title":"Winter wheat yield estimation at the field scale using sentinel-2 data and deep learning","volume":"216","author":"Xiao","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.aei.2026.104762_b7","series-title":"Plant disease phenotype captioning via zero-shot learning with semantic correction based on llm","author":"Xie","year":"2025"},{"key":"10.1016\/j.aei.2026.104762_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2024.108670","article-title":"Real-time detection and counting of wheat ears based on improved YOLOv7","volume":"218","author":"Li","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.aei.2026.104762_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2024.109204","article-title":"APW: An ensemble model for efficient wheat spike counting in unmanned aerial vehicle images","volume":"224","author":"Yao","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.aei.2026.104762_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2022.107439","article-title":"Wheat spike localization and counting via hybrid UNet architectures","volume":"203","author":"Zaji","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.aei.2026.104762_b11","article-title":"Winter wheat yield prediction using linear and nonlinear machine learning algorithms based on climatological and remote sensing data","author":"Haseeb","year":"2025","journal-title":"Inf. Process. Agric."},{"key":"10.1016\/j.aei.2026.104762_b12","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.neucom.2022.03.017","article-title":"Wheatnet: A lightweight convolutional neural network for high-throughput image-based wheat head detection and counting","volume":"489","author":"Khaki","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.aei.2026.104762_b13","doi-asserted-by":"crossref","DOI":"10.3389\/fpls.2019.01176","article-title":"DeepCount: In-field automatic quantification of wheat spikes using simple linear iterative clustering and deep convolutional neural networks","author":"Sadeghi-Tehran","year":"2019","journal-title":"Front. Plant Sci."},{"issue":"2","key":"10.1016\/j.aei.2026.104762_b14","first-page":"240","article-title":"Method for wheat ear counting based on frequency domain decomposition of MSVF-ISCT","volume":"10","author":"Bao","year":"2023","journal-title":"Inf. Process. Agric."},{"key":"10.1016\/j.aei.2026.104762_b15","article-title":"DHS-ViG: Dynamic hierarchical selective graph for comprehensive and robust feature perception","author":"Chen","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.aei.2026.104762_b16","doi-asserted-by":"crossref","DOI":"10.3389\/fpls.2024.1435042","article-title":"FIDMT-GhostNet: A lightweight density estimation model for wheat ear counting","volume":"15","author":"Yang","year":"2024","journal-title":"Front. Plant Sci."},{"key":"10.1016\/j.aei.2026.104762_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2025.110314","article-title":"WSG-P2PNet: A deep learning framework for counting and locating wheat spike grains in the open field environment","volume":"235","author":"Geng","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.aei.2026.104762_b18","doi-asserted-by":"crossref","unstructured":"P. Doubinsky, N. Audebert, M. Crucianu, H. Le Borgne, Semantic generative augmentations for few-shot counting, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 5443\u20135452.","DOI":"10.1109\/WACV57701.2024.00536"},{"key":"10.1016\/j.aei.2026.104762_b19","doi-asserted-by":"crossref","first-page":"48810","DOI":"10.52202\/079017-1547","article-title":"Countgd: Multi-modal open-world counting","volume":"37","author":"Amini-Naieni","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.aei.2026.104762_b20","doi-asserted-by":"crossref","DOI":"10.34133\/2020\/4152816","article-title":"Convolutional neural networks for image-based high-throughput plant phenotyping: A review","author":"Jiang","year":"2020","journal-title":"Plant Phenomics"},{"key":"10.1016\/j.aei.2026.104762_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.cj.2026.01.011","article-title":"LesionDiff: Synthetic data via lesion information transfer diffusion model facilitates plant disease diagnosis","author":"Wu","year":"2026","journal-title":"Crop. J."},{"key":"10.1016\/j.aei.2026.104762_b22","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.neucom.2021.02.103","article-title":"A survey of crowd counting and density estimation based on convolutional neural network","volume":"472","author":"Fan","year":"2022","journal-title":"Neurocomputing"},{"issue":"6","key":"10.1016\/j.aei.2026.104762_b23","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-021-3445-y","article-title":"Transcrowd: Weakly-supervised crowd counting with transformers","volume":"65","author":"Liang","year":"2022","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.aei.2026.104762_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103792","article-title":"Multimodal feature cooperative refinement for few-shot anomaly detection","volume":"68","author":"Xu","year":"2025","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104762_b25","series-title":"Count2Density: Crowd density estimation without location-level annotations","author":"Litrico","year":"2025"},{"key":"10.1016\/j.aei.2026.104762_b26","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.neucom.2020.09.059","article-title":"A multi-scale and multi-level feature aggregation network for crowd counting","volume":"423","author":"Zhu","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.aei.2026.104762_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121272","article-title":"Dual-branch counting method for dense crowd based on self-attention mechanism","volume":"236","author":"Wang","year":"2024","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"10.1016\/j.aei.2026.104762_b28","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1186\/s13007-018-0366-8","article-title":"Detection and analysis of wheat spikes using convolutional neural networks","volume":"14","author":"Hasan","year":"2018","journal-title":"Plant Methods"},{"key":"10.1016\/j.aei.2026.104762_b29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13007-018-0289-4","article-title":"Wheat ear counting in-field conditions: High throughput and low-cost approach using RGB images","volume":"14","author":"Fernandez-Gallego","year":"2018","journal-title":"Plant Methods"},{"key":"10.1016\/j.aei.2026.104762_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.plaphe.2026.100182","article-title":"Leaf-Detr: Progressive adaptive network with lower matching cost for dense leaves detection","author":"Wan","year":"2026","journal-title":"Plant Phenomics"},{"issue":"1","key":"10.1016\/j.aei.2026.104762_b31","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1186\/s13007-019-0537-2","article-title":"TasselNetv2: In-field counting of wheat spikes with context-augmented local regression networks","volume":"15","author":"Xiong","year":"2019","journal-title":"Plant Methods"},{"issue":"5","key":"10.1016\/j.aei.2026.104762_b32","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.1016\/j.cj.2022.07.007","article-title":"Development of image-based wheat spike counter through a Faster R-CNN algorithm and application for genetic studies","volume":"10","author":"Li","year":"2022","journal-title":"Crop. J."},{"key":"10.1016\/j.aei.2026.104762_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2023.107623","article-title":"AutoOLA: Automatic object level augmentation for wheat spikes counting","volume":"205","author":"Zaji","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.aei.2026.104762_b34","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.aei.2026.104762_b35","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.aei.2026.104762_b36","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"},{"key":"10.1016\/j.aei.2026.104762_b37","series-title":"2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems","first-page":"1","article-title":"Yolov8: A novel object detection algorithm with enhanced performance and robustness","author":"Varghese","year":"2024"},{"key":"10.1016\/j.aei.2026.104762_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102709","article-title":"YOLO-MIF: Improved YOLOv8 with multi-information fusion for object detection in gray-scale images","volume":"62","author":"Wan","year":"2024","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104762_b39","first-page":"1","article-title":"Integrating SAM with feature interaction for remote sensing change detection","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.aei.2026.104762_b40","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.aei.2026.104762_b41","article-title":"Cross-attention multi-scale state space model for remaining useful life prediction of aircraft engines","volume":"69","author":"Zhang","year":"2026","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104762_b42","doi-asserted-by":"crossref","DOI":"10.34133\/2021\/9846158","article-title":"Global wheat head detection 2021: An improved dataset for benchmarking wheat head detection methods","author":"David","year":"2021","journal-title":"Plant Phenomics"},{"key":"10.1016\/j.aei.2026.104762_b43","doi-asserted-by":"crossref","unstructured":"Y. Zhang, D. Zhou, S. Chen, S. Gao, Y. Ma, Single-image crowd counting via multi-column convolutional neural network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 589\u2013597.","DOI":"10.1109\/CVPR.2016.70"},{"key":"10.1016\/j.aei.2026.104762_b44","doi-asserted-by":"crossref","unstructured":"Y. Li, X. Zhang, D. Chen, Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 1091\u20131100.","DOI":"10.1109\/CVPR.2018.00120"},{"key":"10.1016\/j.aei.2026.104762_b45","doi-asserted-by":"crossref","DOI":"10.3389\/fpls.2020.541960","article-title":"TasselNetV2+: A fast implementation for high-throughput plant counting from high-resolution RGB imagery","volume":"11","author":"Lu","year":"2020","journal-title":"Front. Plant Sci."},{"key":"10.1016\/j.aei.2026.104762_b46","series-title":"European Conference on Computer Vision","first-page":"428","article-title":"Improving point-based crowd counting and localization based on auxiliary point guidance","author":"Chen","year":"2024"},{"key":"10.1016\/j.aei.2026.104762_b47","doi-asserted-by":"crossref","unstructured":"Q. Song, C. Wang, Z. Jiang, Y. Wang, Y. Tai, C. Wang, J. Li, F. Huang, Y. Wu, Rethinking counting and localization in crowds: A purely point-based framework, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 3365\u20133374.","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"10.1016\/j.aei.2026.104762_b48","series-title":"Clip-ebc: Clip can count accurately through enhanced blockwise classification","author":"Ma","year":"2024"},{"key":"10.1016\/j.aei.2026.104762_b49","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1016\/j.isprsjprs.2025.11.017","article-title":"TasselNetV4: A vision foundation model for cross-scene, cross-scale, and cross-species plant counting","volume":"231","author":"Hu","year":"2026","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.aei.2026.104762_b50","series-title":"Ultralytics YOLOv8","author":"Jocher","year":"2023"},{"key":"10.1016\/j.aei.2026.104762_b51","doi-asserted-by":"crossref","unstructured":"R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra, Grad-cam: Visual explanations from deep networks via gradient-based localization, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"10.1016\/j.aei.2026.104762_b52","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"}],"container-title":["Advanced Engineering Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1474034626004544?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1474034626004544?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:53:56Z","timestamp":1780620836000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1474034626004544"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":52,"alternative-id":["S1474034626004544"],"URL":"https:\/\/doi.org\/10.1016\/j.aei.2026.104762","relation":{},"ISSN":["1474-0346"],"issn-type":[{"value":"1474-0346","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"WheatGOAT: Generalizable object-aware tracker via discriminative region semantic learning for wheat ear counting","name":"articletitle","label":"Article Title"},{"value":"Advanced Engineering Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aei.2026.104762","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":"104762"}}