{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T16:02:07Z","timestamp":1780934527101,"version":"3.54.1"},"reference-count":59,"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"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.engappai.2026.115177","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T21:37:31Z","timestamp":1779745051000},"page":"115177","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P2","title":["A Vision\u2013language joint modeling framework for rubber-tree planting-hole detection in unmanned aerial vehicle imagery"],"prefix":"10.1016","volume":"179","author":[{"given":"Pintian","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wentao","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaowen","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaiqing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengrui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangquan","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shicong","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zidi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amar","family":"Jain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingfang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoxiong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.115177_bib1","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2024.1427786","article-title":"Multi-modal remote perception learning for object sensory data","volume":"18","author":"Almujally","year":"2024","journal-title":"Front. Neurorob."},{"key":"10.1016\/j.engappai.2026.115177_bib2","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2025.1582995","article-title":"Unmanned aerial vehicle based multi-person detection via deep neural network models","volume":"19","author":"Alshehri","year":"2025","journal-title":"Front. Neurorob."},{"issue":"2","key":"10.1016\/j.engappai.2026.115177_bib3","doi-asserted-by":"crossref","first-page":"184","DOI":"10.23887\/janapati.v12i2.60628","article-title":"Hole detection in plastic mulch using template matching and machine learning algorithms","volume":"12","author":"Aziz","year":"2023","journal-title":"Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI"},{"key":"10.1016\/j.engappai.2026.115177_bib4","series-title":"IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium","first-page":"1245","article-title":"Multimodal object detection in remote sensing","author":"Belmouhcine","year":"2023"},{"issue":"6","key":"10.1016\/j.engappai.2026.115177_bib5","doi-asserted-by":"crossref","first-page":"4240","DOI":"10.1109\/TPAMI.2025.3538473","article-title":"YOLO-MS: rethinking multi-scale representation learning for real-time object detection","volume":"47","author":"Chen","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.115177_bib6","article-title":"Cross-modality attentive feature fusion for object detection in multispectral remote sensing imagery","volume":"130","author":"Fang","year":"2022","journal-title":"Pattern Recogn."},{"key":"10.1016\/j.engappai.2026.115177_bib7","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1016\/j.isprsjprs.2021.11.013","article-title":"Unsupervised spectral-spatial processing of drone imagery for identification of pine seedlings","volume":"183","author":"Finn","year":"2022","journal-title":"ISPRS J. Photogrammetry Remote Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib8","article-title":"SIoU loss: more powerful learning for bounding box regression","author":"Gevorgyan","year":"2022","journal-title":"arXiv preprint arXiv:2205.12740"},{"key":"10.1016\/j.engappai.2026.115177_bib9","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13946","article-title":"Heterogeneous grid convolution for adaptive, efficient, and controllable computation","author":"Hamaguchi","year":"2021"},{"key":"10.1016\/j.engappai.2026.115177_bib10","doi-asserted-by":"crossref","first-page":"4887","DOI":"10.3390\/rs15194887","article-title":"Misaligned RGB-infrared object detection via adaptive dual-discrepancy calibration","volume":"15","author":"He","year":"2023","journal-title":"Remote Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib11","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13713","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"},{"issue":"Part 1","key":"10.1016\/j.engappai.2026.115177_bib12","article-title":"LVF: a language and vision fusion framework for tomato diseases segmentation","volume":"227","author":"Hu","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.engappai.2026.115177_bib13","doi-asserted-by":"crossref","first-page":"847","DOI":"10.3390\/rs13050847","article-title":"CF2PN: a cross-scale feature fusion pyramid network based remote sensing target detection","volume":"13","author":"Huang","year":"2021","journal-title":"Remote Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib14","article-title":"Ultralytics YOLOv8","author":"Jocher","year":"2023","journal-title":"GitHub"},{"key":"10.1016\/j.engappai.2026.115177_bib17","doi-asserted-by":"crossref","first-page":"291","DOI":"10.3390\/app14010291","article-title":"CGT-YOLOv5n: a precision model for detecting mouse holes amid complex grassland terrains","volume":"14","author":"Li","year":"2024","journal-title":"Appl. Sci."},{"key":"10.1016\/j.engappai.2026.115177_bib15","article-title":"PolyLoss: a polynomial expansion perspective of classification loss functions","author":"Leng","year":"2022","journal-title":"arXiv preprint arXiv:2204.12511"},{"key":"10.1016\/j.engappai.2026.115177_bib18","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1007\/s11554-024-01436-6","article-title":"Slim-neck by GSConv: a lightweight-design for real-time detector architectures","volume":"21","author":"Li","year":"2024","journal-title":"Journal of Real-Time Image Processing"},{"key":"10.1016\/j.engappai.2026.115177_bib19","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.113260","article-title":"A lightweight YOLOv8-based model with squeeze-and-excitation Version 2 for crack detection of pipelines","volume":"177","author":"Li","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.engappai.2026.115177_bib20","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1109\/JSTARS.2025.3631384","article-title":"CN-UNet: convnext UNet with slicing-aided hyper segmentation for infrared small target detection","volume":"19","author":"Li","year":"2026","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib16","article-title":"Omni-dimensional dynamic convolution","author":"Li","year":"2022","journal-title":"arXiv preprint arXiv:2209.07947"},{"key":"10.1016\/j.engappai.2026.115177_bib21","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6282","article-title":"DynamicDet: a unified dynamic architecture for object detection","author":"Lin","year":"2023"},{"key":"10.1016\/j.engappai.2026.115177_bib22","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.3390\/rs14112616","article-title":"Shadow removal from UAV images based on color and texture equalization compensation of local homogeneous regions","volume":"14","author":"Liu","year":"2022","journal-title":"Remote Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib23","first-page":"1","article-title":"ABNet: adaptive balanced network for multiscale object detection in remote sensing imagery","volume":"60","author":"Liu","year":"2022","journal-title":"IEEE Trans. Geosci. Rem. Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib24","doi-asserted-by":"crossref","first-page":"2614","DOI":"10.3390\/rs17152614","article-title":"Detecting planting holes using improved YOLO-PH algorithm with UAV images","volume":"17","author":"Long","year":"2025","journal-title":"Remote Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib25","article-title":"RTMDet: an empirical study of designing real-time object detectors","author":"Lyu","year":"2022","journal-title":"arXiv preprint arXiv:2212.07784"},{"key":"10.1016\/j.engappai.2026.115177_bib26","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/j.isprsjprs.2024.01.005","article-title":"Hierarchical alignment network for domain adaptive object detection in aerial images","volume":"208","author":"Ma","year":"2024","journal-title":"ISPRS J. Photogrammetry Remote Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib27","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"3139","article-title":"Rotate to attend: convolutional triplet attention module","author":"Misra","year":"2021"},{"key":"10.1016\/j.engappai.2026.115177_bib28","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Efficient multi-scale attention module with cross-spatial learning","author":"Ouyang","year":"2023"},{"key":"10.1016\/j.engappai.2026.115177_bib29","doi-asserted-by":"crossref","first-page":"3794","DOI":"10.1111\/mice.70041","article-title":"A multimodal imaging textual fused channel spatial Kolmogorov\u2013Arnold network for road crack detection","volume":"40","author":"Peng","year":"2025","journal-title":"Comput. Aided Civ. Infrastruct. Eng."},{"key":"10.1016\/j.engappai.2026.115177_bib30","article-title":"CBAM-STN-TPS-YOLO: enhancing agricultural object detection through spatially adaptive attention mechanisms","author":"Praveen","year":"2025","journal-title":"arXiv preprint arXiv:2506.07357"},{"key":"10.1016\/j.engappai.2026.115177_bib31","article-title":"PYCNet: fusion of monochrome polarization camera and LiDAR for road target detection in complex lighting","volume":"1","author":"Qian","year":"2026","journal-title":"IEEE Sens. J."},{"issue":"2","key":"10.1016\/j.engappai.2026.115177_bib32","first-page":"3315","article-title":"Semantic segmentation and YOLO detector over aerial vehicle images","volume":"80","author":"Qureshi","year":"2024","journal-title":"Comput. Mater. Contin."},{"issue":"1","key":"10.1016\/j.engappai.2026.115177_bib33","doi-asserted-by":"crossref","DOI":"10.1080\/15481603.2025.2487334","article-title":"An automatic remote sensing image shadow compensation method utilizing reflectance differences and transfer learning","volume":"62","author":"Shen","year":"2025","journal-title":"GIScience Remote Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib34","article-title":"Hide-and-seek: a data augmentation technique for weakly-supervised localization and beyond","author":"Singh","year":"2018","journal-title":"arXiv preprint arXiv:1811.02545"},{"key":"10.1016\/j.engappai.2026.115177_bib36","doi-asserted-by":"crossref","first-page":"2227","DOI":"10.3390\/agriculture15212227","article-title":"Simple and affordable vision-based detection of seedling deficiencies to relieve labor shortages in small-scale cruciferous nurseries","volume":"15","author":"Su","year":"2025","journal-title":"Agriculture"},{"key":"10.1016\/j.engappai.2026.115177_bib35","article-title":"Occlusion-aware detection and Re-ID calibrated network for multi-object tracking","author":"Su","year":"2023","journal-title":"arXiv preprint arXiv:2308.15795"},{"key":"10.1016\/j.engappai.2026.115177_bib37","article-title":"TGCADNet: Text-Guided context-aware detection via CLIP for small objects in UAV scenes","volume":"1","author":"Sun","year":"2026","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"10.1016\/j.engappai.2026.115177_bib39","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11534","article-title":"ECA-Net: efficient channel attention for deep convolutional neural networks","author":"Wang","year":"2020"},{"key":"10.1016\/j.engappai.2026.115177_bib41","first-page":"107984","article-title":"YOLOv10: Real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.engappai.2026.115177_bib40","doi-asserted-by":"crossref","first-page":"3265","DOI":"10.3390\/rs15133265","article-title":"Small object detection based on deep learning for remote sensing: a comprehensive review","volume":"15","author":"Wang","year":"2023","journal-title":"Remote Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib38","article-title":"Wise-IoU: bounding box regression loss with dynamic focusing mechanism","author":"Tong","year":"2023","journal-title":"arXiv preprint arXiv:2301.10051"},{"key":"10.1016\/j.engappai.2026.115177_bib42","series-title":"Proceedings of the European Conference on Computer Vision","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.1016\/j.engappai.2026.115177_bib43","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2025.111010","article-title":"CT-HiffNet: a contour-texture hierarchical feature fusion network for cropland field parcel extraction from high-resolution remote sensing images","volume":"239","author":"Wu","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.engappai.2026.115177_bib44","article-title":"Accurate UAV-based detection of planting pits via spectral-spatial dual-domain collaboration","volume":"12","author":"Xie","year":"2025","journal-title":"Smart Agric. Technol."},{"key":"10.1016\/j.engappai.2026.115177_bib45","article-title":"PKNet: infrared small target detection via parallel interactive Kolmogorov-Arnold network","volume":"1","author":"Yan","year":"2025","journal-title":"IEEE Trans. Geosci. Rem. Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib46","article-title":"CondConv: conditionally parameterized convolutions for efficient inference","volume":"32","author":"Yang","year":"2019"},{"key":"10.1016\/j.engappai.2026.115177_bib47","series-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","article-title":"SimAM: a simple, parameter-free attention module for convolutional neural networks","author":"Yang","year":"2021"},{"key":"10.1016\/j.engappai.2026.115177_bib48","doi-asserted-by":"crossref","first-page":"2034","DOI":"10.1109\/TIP.2026.3661417","article-title":"PestScope: Exclusion-Aware large multimodal model for fine-grained agricultural Pest segmentation","volume":"35","author":"Yang","year":"2026","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.engappai.2026.115177_bib49","first-page":"1","article-title":"C2Former: calibrated and complementary transformer for RGB-infrared object detection","volume":"62","author":"Yuan","year":"2024","journal-title":"IEEE Trans. Geosci. Rem. Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib50","doi-asserted-by":"crossref","first-page":"862","DOI":"10.3390\/rs13050862","article-title":"Object detection in remote sensing images via multi-feature pyramid network with receptive field block","volume":"13","author":"Yuan","year":"2021","journal-title":"Remote Sens."},{"issue":"12","key":"10.1016\/j.engappai.2026.115177_bib51","doi-asserted-by":"crossref","first-page":"10015","DOI":"10.1109\/TGRS.2019.2930982","article-title":"CAD-Net: a context-aware detection network for objects in remote sensing imagery","volume":"57","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Geosci. Rem. Sens."},{"key":"10.1016\/j.engappai.2026.115177_bib52","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","article-title":"Focal and efficient IoU loss for accurate bounding box regression","volume":"506","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"issue":"4","key":"10.1016\/j.engappai.2026.115177_bib54","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.1080\/10589759.2024.2395363","article-title":"UAV based defect detection and fault diagnosis for static and rotating wind turbine blade: a review","volume":"40","author":"Zhang","year":"2025","journal-title":"Nondestr. Test. Eval."},{"key":"10.1016\/j.engappai.2026.115177_bib53","article-title":"Inner-IoU: more effective intersection over union loss with auxiliary bounding box","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2311.02877"},{"key":"10.1016\/j.engappai.2026.115177_bib55","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16965","article-title":"DETRs beat YOLOs on real-time object detection","author":"Zhao","year":"2024"},{"key":"10.1016\/j.engappai.2026.115177_bib56","article-title":"Towards robust optical-SAR object detection under missing modalities: a dynamic quality-aware fusion framework","author":"Zhao","year":"2025","journal-title":"arXiv preprint arXiv:2512.22447"},{"key":"10.1016\/j.engappai.2026.115177_bib57","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16793","article-title":"RegionCLIP: Region-based language-image pretraining","author":"Zhong","year":"2022"},{"key":"10.1016\/j.engappai.2026.115177_bib58","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9308","article-title":"Deformable ConvNets V2: more deformable, better results","author":"Zhu","year":"2019"},{"issue":"19","key":"10.1016\/j.engappai.2026.115177_bib59","doi-asserted-by":"crossref","first-page":"3608","DOI":"10.3390\/rs16193608","article-title":"Infrared weak target detection in dual images and dual areas","volume":"16","author":"Zhuang","year":"2024","journal-title":"Remote Sens."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626014612?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626014612?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:47:48Z","timestamp":1780933668000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626014612"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":59,"alternative-id":["S0952197626014612"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115177","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A Vision\u2013language joint modeling framework for rubber-tree planting-hole detection in unmanned aerial vehicle imagery","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115177","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":"115177"}}