{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:07:25Z","timestamp":1789038445143,"version":"build-2803163510"},"reference-count":41,"publisher":"Elsevier BV","issue":"4","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,9]],"date-time":"2026-08-09T00:00:00Z","timestamp":1786233600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100005825","name":"National Institute of Food and Agriculture","doi-asserted-by":"publisher","award":["2022-51181-38240"],"award-info":[{"award-number":["2022-51181-38240"]}],"id":[{"id":"10.13039\/100005825","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005825","name":"National Institute of Food and Agriculture","doi-asserted-by":"publisher","award":["2023-67021-40646"],"award-info":[{"award-number":["2023-67021-40646"]}],"id":[{"id":"10.13039\/100005825","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Plant Phenomics"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.plaphe.2026.100264","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T23:33:21Z","timestamp":1786577601000},"page":"100264","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["SAM-CLIP-Thermal: Leveraging large multimodal models for reliable and scalable annotation in thermal image segmentation for field plant phenotyping"],"prefix":"10.1016","volume":"8","author":[{"given":"Yiyuan","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenjiao","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changying","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4495-3033","authenticated-orcid":false,"given":"Yu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.plaphe.2026.100264_bib1","doi-asserted-by":"crossref","DOI":"10.34133\/2020\/4152816","article-title":"Convolutional neural networks for image-based high-throughput plant phenotyping: a review","volume":"2020","author":"Jiang","year":"2020","journal-title":"Plant Phenomics"},{"key":"10.1016\/j.plaphe.2026.100264_bib2","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109412","article-title":"Recent advances in transformer technology for agriculture: a comprehensive survey","volume":"138","author":"Xie","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"2","key":"10.1016\/j.plaphe.2026.100264_bib3","first-page":"172","article-title":"Semantic segmentation of agricultural images: a survey","volume":"11","author":"Luo","year":"2024","journal-title":"Inf. Process. Agric."},{"issue":"6","key":"10.1016\/j.plaphe.2026.100264_bib4","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s10462-024-10775-6","article-title":"Deep learning implementation of image segmentation in agricultural applications: a comprehensive review","volume":"57","author":"Lei","year":"2024","journal-title":"Artif. Intell. Rev."},{"issue":"2","key":"10.1016\/j.plaphe.2026.100264_bib5","doi-asserted-by":"crossref","first-page":"472","DOI":"10.3390\/s25020472","article-title":"A review of CNN applications in smart agriculture using multimodal data","volume":"25","author":"El Sakka","year":"2025","journal-title":"Sensors"},{"key":"10.1016\/j.plaphe.2026.100264_bib6","article-title":"Caltech aerial rgb-thermal dataset in the wild","author":"Lee","year":"2024","journal-title":"arXiv:2403.08997"},{"key":"10.1016\/j.plaphe.2026.100264_bib7","article-title":"Semantics from space: Satellite-guided thermal semantic segmentation annotation for aerial field robots","author":"Lee","year":"2024","journal-title":"arXiv:2403.14056"},{"key":"10.1016\/j.plaphe.2026.100264_bib8","article-title":"Domain adaptation for big data in agricultural image analysis: a comprehensive review","author":"Hu","year":"2025","journal-title":"arXiv:2506.05972"},{"key":"10.1016\/j.plaphe.2026.100264_bib9","series-title":"2023 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","first-page":"130","article-title":"Thermalsynth: a novel approach for generating synthetic thermal human scenarios","author":"Madan","year":"2023"},{"key":"10.1016\/j.plaphe.2026.100264_bib10","article-title":"T-fake: synthesizing thermal images for facial landmarking","author":"Flotho","year":"2025","journal-title":"arXiv:2408.15127"},{"issue":"10","key":"10.1016\/j.plaphe.2026.100264_bib11","doi-asserted-by":"crossref","first-page":"3909","DOI":"10.1109\/TMI.2025.3532084","article-title":"Stitching, fine-tuning, and re-training: a sam-enabled framework for semi-supervised 3d medical image segmentation","volume":"44","author":"Li","year":"2025","journal-title":"IEEE Trans. Med. Imag."},{"issue":"8","key":"10.1016\/j.plaphe.2026.100264_bib12","doi-asserted-by":"crossref","DOI":"10.3390\/agriculture15080847","article-title":"Foundation models in agriculture: a comprehensive review","volume":"15","author":"Yin","year":"2025","journal-title":"Agriculture"},{"key":"10.1016\/j.plaphe.2026.100264_bib13","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2024.109032","article-title":"Foundation models in smart agriculture: basics, opportunities, and challenges","volume":"222","author":"Li","year":"2024","journal-title":"Comput. Electron. Agric."},{"issue":"16","key":"10.1016\/j.plaphe.2026.100264_bib14","doi-asserted-by":"crossref","DOI":"10.3390\/app15169206","article-title":"Agricultural image processing: challenges, advances, and future trends","volume":"15","author":"Song","year":"2025","journal-title":"Appl. Sci."},{"key":"10.1016\/j.plaphe.2026.100264_bib15","article-title":"On the promises and challenges of multimodal foundation models for geographical, environmental, agricultural, and urban planning applications","author":"Tan","year":"2023","journal-title":"arXiv:2312.17016"},{"key":"10.1016\/j.plaphe.2026.100264_bib16","article-title":"Segment anything","author":"Kirillov","year":"2023","journal-title":"arXiv:2304.02643"},{"key":"10.1016\/j.plaphe.2026.100264_bib17","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"10.1016\/j.plaphe.2026.100264_bib18","series-title":"2024 ASABE Annual International Meeting","first-page":"1","article-title":"Effective integration of vision foundational models for semantic segmentation to quantify grape foliage powdery mildew infection","author":"Lin","year":"2024"},{"key":"10.1016\/j.plaphe.2026.100264_bib19","series-title":"Integrating Large multi-modal Models for Automated Powdery Mildew Phenotyping in Grapevines","author":"Lin","year":"2026"},{"issue":"1","key":"10.1016\/j.plaphe.2026.100264_bib20","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1002\/rob.21877","article-title":"A high-resolution, multimodal data set for agricultural robotics: a ladybird\u2019s-eye view of brassica","volume":"37","author":"Bender","year":"2020","journal-title":"J. Field Robot."},{"key":"10.1016\/j.plaphe.2026.100264_bib21","series-title":"2018 ASABE Annual International Meeting","first-page":"1","article-title":"Deep learning for thermal image segmentation to measure canopy temperature of Brassica oleracea in the field","author":"Jiang","year":"2018"},{"issue":"1","key":"10.1016\/j.plaphe.2026.100264_bib22","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.1038\/s41598-018-19142-2","article-title":"Gphenovision: a ground mobile system with multi-modal imaging for field-based high throughput phenotyping of cotton","volume":"8","author":"Jiang","year":"2018","journal-title":"Sci. Rep."},{"key":"10.1016\/j.plaphe.2026.100264_bib23","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015","journal-title":"arXiv:1505.04597"},{"key":"10.1016\/j.plaphe.2026.100264_bib24","article-title":"K-net: towards unified image segmentation","author":"Zhang","year":"2021","journal-title":"arXiv:2106.14855"},{"key":"10.1016\/j.plaphe.2026.100264_bib25","article-title":"Segformer: simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021","journal-title":"arXiv:2105.15203"},{"key":"10.1016\/j.plaphe.2026.100264_bib26","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"233","article-title":"IRSAM: advancing segment anything model for infrared small target detection","author":"Zhang","year":"2025"},{"key":"10.1016\/j.plaphe.2026.100264_bib27","article-title":"SAM 3: segment anything with concepts","author":"Carion","year":"2025","journal-title":"arXiv:2511.16719"},{"key":"10.1016\/j.plaphe.2026.100264_bib28","author":"Contributors"},{"key":"10.1016\/j.plaphe.2026.100264_bib29","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3213","article-title":"The cityscapes dataset for semantic urban scene understanding","author":"Cordts","year":"2016"},{"key":"10.1016\/j.plaphe.2026.100264_bib30","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5122","article-title":"Scene parsing through ade20k dataset","author":"Zhou","year":"2017"},{"key":"10.1016\/j.plaphe.2026.100264_bib31","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2023.108114","article-title":"From one field to another\u2014unsupervised domain adaptation for semantic segmentation in agricultural robotics","volume":"212","author":"Magistri","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.plaphe.2026.100264_bib32","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops","first-page":"7080","article-title":"Agmic: agricultural masked image consistency for cross-domain segmentation","author":"Ullah","year":"2025"},{"key":"10.1016\/j.plaphe.2026.100264_bib33","doi-asserted-by":"crossref","first-page":"21300","DOI":"10.1109\/ACCESS.2023.3249759","article-title":"Assessing inter-annotator agreement for medical image segmentation","volume":"11","author":"Yang","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.plaphe.2026.100264_bib34","first-page":"23","article-title":"What can we learn from inter-annotator variability in skin lesion segmentation?","volume":"16149","author":"Abhishek","year":"2025"},{"issue":"19","key":"10.1016\/j.plaphe.2026.100264_bib35","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1080\/01691864.2022.2109427","article-title":"Multi-source pseudo-label learning of semantic segmentation for the scene recognition of agricultural mobile robots","volume":"36","author":"Matsuzaki","year":"2022","journal-title":"Adv. Robot."},{"key":"10.1016\/j.plaphe.2026.100264_bib36","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","first-page":"2484","article-title":"Unsupervised domain adaptation for weed segmentation using greedy pseudo-labelling","author":"Huang","year":"2024"},{"issue":"8","key":"10.1016\/j.plaphe.2026.100264_bib37","doi-asserted-by":"crossref","DOI":"10.3390\/agriengineering7080248","article-title":"Tom-ssl: tomato disease recognition using pseudo-labelling-based semi-supervised learning","volume":"7","author":"Nishankar","year":"2025","journal-title":"AgriEngineering"},{"key":"10.1016\/j.plaphe.2026.100264_bib38","article-title":"Learning to \u201dsegment anything\u201d in thermal infrared images through knowledge distillation with a large scale dataset satir","author":"Chen","year":"2023","journal-title":"arXiv:2304.07969"},{"key":"10.1016\/j.plaphe.2026.100264_bib39","series-title":"2025 3rd International Conference on Inventive Computing and Informatics (ICICI)","first-page":"751","article-title":"Semantic segmentation for early detection of plant stress and disease using multispectral and thermal imaging through u-net based model","author":"Reddy","year":"2025"},{"key":"10.1016\/j.plaphe.2026.100264_bib40","article-title":"Thermal canopy segmentation in tomato plants: a novel approach with integration of yolov8-c and fastsam","volume":"10","author":"P","year":"2025","journal-title":"Smart Agric. Technol."},{"key":"10.1016\/j.plaphe.2026.100264_bib41","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2020.105678","article-title":"Recognition method of thermal infrared images of plant canopies based on the characteristic registration of heterogeneous images","volume":"177","author":"Liu","year":"2020","journal-title":"Comput. Electron. Agric."}],"container-title":["Plant Phenomics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2643651526001019?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2643651526001019?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:16:30Z","timestamp":1789035390000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2643651526001019"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["S2643651526001019"],"URL":"https:\/\/doi.org\/10.1016\/j.plaphe.2026.100264","relation":{},"ISSN":["2643-6515"],"issn-type":[{"value":"2643-6515","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SAM-CLIP-Thermal: Leveraging large multimodal models for reliable and scalable annotation in thermal image segmentation for field plant phenotyping","name":"articletitle","label":"Article Title"},{"value":"Plant Phenomics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.plaphe.2026.100264","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V. on behalf of Nanjing Agricultural University.","name":"copyright","label":"Copyright"}],"article-number":"100264"}}