{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:04:06Z","timestamp":1789380246809,"version":"build-2803163510"},"reference-count":116,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Natural history museums house invaluable biodiversity archives, but discoveries are often limited by the accessibility of collections data. As digitization of specimens and metadata accelerates, automated methods are needed to organize image databases and enable large-scale analyses. Beyond species identification, computer vision (CV) can automate image database management by standardizing gallery displays through intelligent cropping and extracting tags to improve search functionality. Encyclopedia of Life is a biodiversity database that aims to document all \u223c2.2 million known species. Using EOL images and crowdsourced data, combined with pretrained and custom-trained models, we present 14 CV pipelines in three categories: Object Detection for Image Cropping, Object Detection for Image Tagging, and Classification for Image Tagging. Pipelines are open source, available on GitHub (https:\/\/github.com\/EOL\/computer-vision-with-EOL-images), and documented for nonexperts. We share models, datasets, and methodological insights demonstrating how CV can unlock novel information from over 1.5 million images.<\/jats:p>","DOI":"10.1093\/biosci\/biag074","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T11:34:59Z","timestamp":1779190499000},"page":"813-831","source":"Crossref","is-referenced-by-count":0,"title":["Manage your image database with computer vision\u2014Lessons learned at Encyclopedia of Life"],"prefix":"10.1093","volume":"76","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6025-4569","authenticated-orcid":false,"given":"K","family":"Wolcott","sequence":"first","affiliation":[{"name":"National Museum of Natural History, Smithsonian Institution , Washington, D.C., 20560 ,","place":["United States"]},{"name":"Florida Museum of Natural History, University of Florida , Gainesville, FL 32611 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J","family":"Hammock","sequence":"additional","affiliation":[{"name":"National Museum of Natural History, Smithsonian Institution , Washington, D.C., 20560 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"K","family":"Schulz","sequence":"additional","affiliation":[{"name":"National Museum of Natural History, Smithsonian Institution , Washington, D.C., 20560 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T M","family":"Orrell","sequence":"additional","affiliation":[{"name":"National Museum of Natural History, Smithsonian Institution , Washington, D.C., 20560 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"2026091405170395900_bib1","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","volume-title":"OSDI \u201916: Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation; 2\u20134 November 2016","author":"Abadi","year":"2015"},{"key":"2026091405170395900_bib2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.03193","article-title":"Recent advances in object detection in the age of deep convolutional neural networks","author":"Agarwal","year":"2018","journal-title":"arXiv"},{"key":"2026091405170395900_bib3","doi-asserted-by":"publisher","DOI":"10.1109\/SocialInformatics.2012.10","article-title":"Visually exploring social participation in Encyclopedia of Life","volume-title":"Proceedings of the 2012 ASE International Conference on Social Informatics; 14\u201316 December 2012","author":"Ahn","year":"2012"},{"key":"2026091405170395900_bib4","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1080\/1743873X.2018.1557665","article-title":"Online volunteering at DigiVol: An innovative crowd-sourcing approach for heritage tourism artefacts preservation","volume":"15","author":"Alony","year":"2020","journal-title":"Journal of Heritage Tourism"},{"key":"2026091405170395900_bib5","doi-asserted-by":"publisher","DOI":"10.1111\/nph.70447","article-title":"Herbariograph: A deep-learning tool to classify specimen images","author":"\u00c1vila","year":"2025","journal-title":"New Phytologist"},{"key":"2026091405170395900_bib6","doi-asserted-by":"publisher","DOI":"10.1088\/1755-1315\/1412\/1\/012023","article-title":"Biodiversity data crowdsourcing: A way forward","volume-title":"12th IGRSM International Conference and Exhibition on Geospatial & Remote Sensing; 29\u201330 April 2024","author":"Azmy","year":"2024"},{"key":"2026091405170395900_bib7","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: A survey and taxonomy","volume":"41","author":"Baltru\u0161aitis","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2026091405170395900_bib8","doi-asserted-by":"publisher","first-page":"581","DOI":"10.12705\/623.16","article-title":"The SALIX method: A semi-automated workflow for herbarium specimen digitization","volume":"62","author":"Barber","year":"2013","journal-title":"Taxon"},{"key":"2026091405170395900_bib9","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-025-05708-z","article-title":"Machine learning training data: Over 500,000 images of butterflies and moths (Lepidoptera) with species labels","volume":"12","author":"Barkmann","year":"2025","journal-title":"Scientific Data"},{"key":"2026091405170395900_bib10","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1037\/1089-2680.5.4.323","article-title":"Bad is stronger than good","volume":"5","author":"Baumeister","year":"2001","journal-title":"Review of General Psychology"},{"key":"2026091405170395900_bib11","doi-asserted-by":"publisher","first-page":"101896","DOI":"10.1016\/j.ecoinf.2022.101896","article-title":"Embracing imperfection: Machine-assisted invertebrate classification in real-world datasets","volume":"72","author":"Blair","year":"2022","journal-title":"Ecological Informatics"},{"key":"2026091405170395900_bib12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020","journal-title":"arXiv"},{"key":"2026091405170395900_bib13","doi-asserted-by":"publisher","first-page":"1640","DOI":"10.1111\/2041-210X.13901","article-title":"Deep learning as a tool for ecology and evolution","volume":"13","author":"Borowiec","year":"2022","journal-title":"Methods in Ecology and Evolution"},{"key":"2026091405170395900_bib14","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.neunet.2018.07.011","article-title":"A systematic study of the class imbalance problem in convolutional neural networks","volume":"106","author":"Buda","year":"2018","journal-title":"Neural Networks"},{"key":"2026091405170395900_bib15","article-title":"ChatGPT. OpenAI. 2023","author":"ChatGPT"},{"key":"2026091405170395900_bib16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.09333","article-title":"Prompt-CAM: Making vision transformers interpretable for fine-grained analysis","author":"Chowdhury","year":"2025","journal-title":"arXiv"},{"key":"2026091405170395900_bib17","article-title":"Computer vision with EOL images. EOL","author":"Computer Vision with EOL Images GitHub"},{"key":"2026091405170395900_bib18","article-title":"darkflow. thtrieu","author":"Darkflow GitHub","year":"2026"},{"key":"2026091405170395900_bib19","article-title":"darknet. pjreddie","author":"Darknet GitHub"},{"key":"2026091405170395900_bib20","doi-asserted-by":"publisher","DOI":"10.1109\/CTEMS.2018.8769211","article-title":"A comparative analysis of gradient descent-based optimization algorithms on convolutional neural network","volume-title":"Proceedings of the International Conference on Computational Techniques, Electronics and Mechanical Systems; 21\u201323 December 2018","author":"Dogo","year":"2018"},{"key":"2026091405170395900_bib21","doi-asserted-by":"publisher","first-page":"15","DOI":"10.3897\/phytokeys.38.7168","article-title":"The use of optical character recognition (OCR) in the digitisation of herbarium specimen labels","volume":"38","author":"Drinkwater","year":"2014","journal-title":"PhytoKeys"},{"key":"2026091405170395900_bib22","doi-asserted-by":"publisher","first-page":"2260","DOI":"10.1111\/2041-210X.70140","article-title":"Optimizing image capture for computer vision-powered taxonomic identification and trait recognition of biodiversity specimens","volume":"16","author":"East","year":"2025","journal-title":"Methods in Ecology and Evolution"},{"key":"2026091405170395900_bib23","article-title":"Encyclopedia of life advanced programming interface (API). EOL","author":"EOL API"},{"key":"2026091405170395900_bib24","unstructured":"EOL CV Datasets on Zenodo . EOL Computer Vision datasets. Zenodo. (27 March 2026; =1&s=10&sort=bestmatch\"&gt;https:\/\/zenodo.org\/communities\/eol\/records?q=%22eol%20computer%20vision%20pipelines%22&l=list&p=1&s=10&sort=bestmatch\"&gt;=1&s=10&sort=bestmatch)"},{"key":"2026091405170395900_bib25","article-title":"EOL Model Zoo. Kaggle","author":"EOL Model Zoo"},{"key":"2026091405170395900_bib26","article-title":"Encyclopedia of Life. EOL","author":"EOL"},{"key":"2026091405170395900_bib27","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (VOC) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"International Journal of Computer Vision"},{"key":"2026091405170395900_bib28","doi-asserted-by":"publisher","DOI":"10.1002\/aps3.11563","article-title":"FloraTraiter: Automated parsing of traits from descriptive biodiversity literature","volume":"12","author":"Folk","year":"2024","journal-title":"Applications in Plant Sciences"},{"key":"2026091405170395900_bib29","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF00344251","article-title":"Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position","volume":"36","author":"Fukushima","year":"1980","journal-title":"Biological Cybernetics"},{"key":"2026091405170395900_bib30","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1098\/rstb.2003.1442","article-title":"Automated species identification: Why not?","volume":"359","author":"Gaston","year":"2004","journal-title":"Philosophical Transactions of the Royal Society of London Series B: Biological Sciences"},{"key":"2026091405170395900_bib31","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","article-title":"Shortcut learning in deep neural networks","volume":"2","author":"Geirhos","year":"2020","journal-title":"Nature Machine Intelligence"},{"key":"2026091405170395900_bib32","article-title":"Plant identification based on noisy web data: The amazing performance of deep learning (LifeCLEF 2017)","volume-title":"Workshop Proceedings of Conference and Labs of the Evaluation Forum (CLEF 2017); 11\u201314 Sep 2017","author":"Go\u00ebau","year":"2017"},{"key":"2026091405170395900_bib33","article-title":"Google Colab. Google","author":"Google Colab Pro Signup"},{"key":"2026091405170395900_bib34","unstructured":"Google Open Images . Open Images Dataset V7 and Extensions (27 March 2026; https:\/\/storage.googleapis.com\/openimages\/web\/index.html)"},{"key":"2026091405170395900_bib35","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1038\/s41580-021-00407-0","article-title":"A guide to machine learning for biologists","volume":"23","author":"Greener","year":"2022","journal-title":"Nature Reviews Molecular Cell Biology"},{"key":"2026091405170395900_bib36","doi-asserted-by":"publisher","first-page":"e109439","DOI":"10.3897\/BDJ.11.e109439","article-title":"Envisaging a global infrastructure to exploit the potential of digitised collections","volume":"11","author":"Groom","year":"2023","journal-title":"Biodiversity Data Journal"},{"key":"2026091405170395900_bib37","unstructured":"Ground truths versus model predictions . Zenodo. Katherine Wolcott. (27 March 2026; 10.5281\/zenodo.14853913)."},{"key":"2026091405170395900_bib38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-025-11408-2","article-title":"A review of artificial intelligence in herbarium specimen image analysis","volume":"58","author":"Guo","year":"2025","journal-title":"Artificial Intelligence Review"},{"key":"2026091405170395900_bib39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.03385","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv"},{"key":"2026091405170395900_bib40","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1093\/biosci\/biz163","article-title":"Digitization and the Future of Natural History Collections","volume":"70","author":"Hedrick","year":"2020","journal-title":"BioScience"},{"key":"2026091405170395900_bib41","doi-asserted-by":"crossref","first-page":"e54280","DOI":"10.3897\/rio.6.e54280","article-title":"Conceptual design blueprint for the DiSSCo digitization infrastructure - DELIVERABLE D8.1","volume":"6","author":"Hardisty","year":"2020","journal-title":"Research Ideas and Outcomes"},{"key":"2026091405170395900_bib42","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Networks"},{"key":"2026091405170395900_bib43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351","article-title":"Speed\/accuracy trade-offs for modern convolutional object detectors","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 21-26 July 2017","author":"Huang","year":"2017"},{"key":"2026091405170395900_bib44","article-title":"Hugging Face Models","author":"Hugging Face Models"},{"key":"2026091405170395900_bib45","article-title":"iDigBio","author":"iDigBio"},{"key":"2026091405170395900_bib46","article-title":"ImageNet","author":"ImageNet"},{"key":"2026091405170395900_bib47","article-title":"imgaug. aleju","author":"Imgaug GitHub"},{"key":"2026091405170395900_bib48","article-title":"iNaturalist","author":"iNaturalist"},{"key":"2026091405170395900_bib49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-65813-1_24","article-title":"LifeCLEF 2017 lab overview: Multimedia species identification challenges","volume-title":"Proceedings of the 2017 International Conference of the Cross-Language Evaluation Forum for European Languages (CLEF); 11\u201314 Sep 2017","author":"Joly","year":"2017"},{"key":"2026091405170395900_bib50","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.05861","article-title":"Interpretable visualizations of data spaces for classification problems","author":"Jorgensen","year":"2025","journal-title":"arXiv"},{"key":"2026091405170395900_bib51","article-title":"Kaggle","author":"Kaggle"},{"key":"2026091405170395900_bib52","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017","journal-title":"arXiv"},{"key":"2026091405170395900_bib53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/database\/bay103","article-title":"Toward a service-based workflow for automated information extraction from herbarium specimens","volume":"2018","author":"Kirchhoff","year":"2018","journal-title":"Database"},{"key":"2026091405170395900_bib54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3897\/BDJ.9.e69806","article-title":"Comprehensive leaf size traits dataset for seven plant species from digitised herbarium specimen images covering more than two centuries","volume":"9","author":"Kommineni","year":"2021","journal-title":"Biodiversity Data Journal"},{"key":"2026091405170395900_bib55","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Advances in Neural Information Processing Systems. 1097\u20131105; 27 March 2026","author":"Krizhevsky","year":"2012"},{"key":"2026091405170395900_bib56","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","article-title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","volume":"128","author":"Kuznetsova","year":"2020","journal-title":"International Journal of Computer Vision"},{"key":"2026091405170395900_bib57","first-page":"255","article-title":"Convolutional networks for images, speech, and time-series","volume-title":"The Handbook of Brain Theory and Neural Networks","author":"LeCun","year":"1995"},{"key":"2026091405170395900_bib58","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2026091405170395900_bib59","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/3-540-46805-6_19","article-title":"Object recognition with gradient-based learning","volume-title":"Shape, Contour, and Grouping in Computer Vision","author":"LeCun","year":"1999"},{"key":"2026091405170395900_bib60","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1093\/biosci\/biz140","article-title":"The extended specimen network: A strategy to enhance us biodiversity collections, promote research and education","volume":"70","author":"Lendemer","year":"2020","journal-title":"BioScience"},{"key":"2026091405170395900_bib61","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017","journal-title":"arXiv"},{"key":"2026091405170395900_bib62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2","article-title":"SSD: Single shot multibox detector","volume-title":"Computer Vision\u2014ECCV 2016: 14th European Conference, 11-14 October 2016","author":"Liu","year":"2016"},{"key":"2026091405170395900_bib63","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/aps3.1233","article-title":"Toward a large-scale and deep phenological stage annotation of herbarium specimens: Case studies from temperate, tropical, and equatorial floras","volume":"7","author":"Lorieul","year":"2019","journal-title":"Applications in Plant Sciences"},{"key":"2026091405170395900_bib64","doi-asserted-by":"publisher","first-page":"642774","DOI":"10.3389\/fevo.2021.642774","article-title":"Computer vision, machine learning, and the promise of phenomics in ecology and evolutionary biology","volume":"9","author":"L\u00fcrig","year":"2021","journal-title":"Frontiers in Ecology and Evolution"},{"key":"2026091405170395900_bib65","article-title":"mAP. Cartucho","author":"mAP GitHub"},{"key":"2026091405170395900_bib66","doi-asserted-by":"publisher","DOI":"10.17161\/bi.v12i0.6646","article-title":"Crowdsourcing natural history archives: Tools for extracting transcriptions and data","volume":"12","author":"Mika","year":"2017","journal-title":"Biodiversity Informatics"},{"key":"2026091405170395900_bib67","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1093\/sysbio\/syaa026","article-title":"Repositories for Taxonomic Data: Where We Are and What is Missing","volume":"69","author":"Miralles","year":"2020","journal-title":"Systematic Biology"},{"key":"2026091405170395900_bib68","unstructured":"MS COCO Dataset . Common Images in Context. Microsoft. (27 March 2026; https:\/\/cocodataset.org\/)."},{"key":"2026091405170395900_bib69","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1811.03378","article-title":"Activation functions: Comparison of trends in practice and research for deep learning","author":"Nwankpa","year":"2018","journal-title":"arXiv"},{"key":"2026091405170395900_bib70","doi-asserted-by":"publisher","first-page":"20242748","DOI":"10.1098\/rspb.2024.2748","article-title":"Phenological patterns of tropical mountain forest trees across the neotropics: Evidence from herbarium specimens","volume":"292","author":"Ordo\u00f1ez","year":"2025","journal-title":"Proceedings of the Royal Society B: Biological Sciences"},{"key":"2026091405170395900_bib71","doi-asserted-by":"publisher","first-page":"e21271","DOI":"10.3897\/BDJ.5.e21271","article-title":"A crowdsourcing approach to collecting photobased insect and plant observation records","volume":"5","author":"Osawa","year":"2017","journal-title":"Biodiversity Data Journal"},{"key":"2026091405170395900_bib72","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1111\/1365-2745.14047","article-title":"Herbarium records provide reliable phenology estimates in the understudied tropics","volume":"111","author":"Park","year":"2023","journal-title":"Journal of Ecology"},{"key":"2026091405170395900_bib73","doi-asserted-by":"publisher","first-page":"e1079","DOI":"10.3897\/BDJ.2.e1079","article-title":"The Encyclopedia of Life v2: Providing global access to knowledge about life on earth","volume":"2","author":"Parr","year":"2014","journal-title":"Biodiversity Data Journal"},{"key":"2026091405170395900_bib74","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.01703","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"arXiv","author":"Paszke","year":"2019"},{"key":"2026091405170395900_bib75","doi-asserted-by":"publisher","first-page":"2611","DOI":"10.1111\/2041-210X.14167","article-title":"A deep learning approach to photo\u2013identification demonstrates high performance on two dozen cetacean species","volume":"14","author":"Patton","year":"2023","journal-title":"Methods in Ecology and Evolution"},{"key":"2026091405170395900_bib76","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1093\/biosci\/biaa044","article-title":"Machine learning using digitized herbarium specimens to advance phenological research","volume":"70","author":"Pearson","year":"2020","journal-title":"BioScience"},{"key":"2026091405170395900_bib77","article-title":"Computer vision with EOL images GitHub","author":"Play for Beginners Notebooks","journal-title":"EOL"},{"key":"2026091405170395900_bib78","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/s00435-025-00747-x","article-title":"Deep learning on field photography reveals the morphometric diversity of Colombian freshwater fish","volume":"144","author":"Poveda-Cuellar","year":"2025","journal-title":"Zoomorphology"},{"key":"2026091405170395900_bib79","article-title":"PyTorch Hub for Researchers","author":"PyTorch Hub"},{"key":"2026091405170395900_bib80","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"arXiv","author":"Radford","year":"2021"},{"key":"2026091405170395900_bib81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91","article-title":"You only look once: Unified, real-time object detection","volume-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; 27\u201330 June 2016","author":"Redmon","year":"2016"},{"key":"2026091405170395900_bib82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690","article-title":"YOLO9000: Better, faster, stronger","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 21-26 July 2017","author":"Redmon","year":"2017"},{"key":"2026091405170395900_bib83","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv"},{"key":"2026091405170395900_bib84","article-title":"Real-time flying object detection with YOLOv8","author":"Reis","year":"2023","journal-title":"arXiv"},{"key":"2026091405170395900_bib85","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2026091405170395900_bib86","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"2026091405170395900_bib87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474","article-title":"MobileNetV2: Inverted residuals and linear bottlenecks","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 18\u201323 June 2018","author":"Sandler","year":"2018"},{"key":"2026091405170395900_bib88","article-title":"Scikit-learn","author":"Scikit-learn"},{"key":"2026091405170395900_bib89","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i27.35060","article-title":"Divshift: Exploring domain-specific distribution shifts in large-scale, volunteer-collected biodiversity datasets","volume-title":"39th Proceedings of the AAAI Conference on Artificial Intelligence; February 25\u2013March 4, 2025","author":"Sierra","year":"2025"},{"key":"2026091405170395900_bib90","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.10104","article-title":"DINOv3","author":"Sim\u00e9oni","year":"2025","journal-title":"arXiv"},{"key":"2026091405170395900_bib91","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2579215","article-title":"Zooniverse: Observing the world\u2019s largest citizen science platform","volume-title":"WWW'14 Companion: Proceedings of the 23rd International Conference on World Wide Web; 7\u201311 April 2014","author":"Simpson","year":"2014"},{"key":"2026091405170395900_bib92","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-87210-1","article-title":"Assessing the potential for deep learning and computer vision to identify bumble bee species from images","volume":"11","author":"Spiesman","year":"2021","journal-title":"Scientific Reports"},{"key":"2026091405170395900_bib93","doi-asserted-by":"publisher","first-page":"e160553","DOI":"10.3897\/bdj.13.e160553","article-title":"SpeciMate: Improving metadata extraction from digitised biological specimens","volume":"13","author":"Stenhouse","year":"2025","journal-title":"Biodiversity Data Journal"},{"key":"2026091405170395900_bib94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01836","article-title":"Bioclip: A vision foundation model for the tree of life","author":"Stevens","year":"2024"},{"key":"2026091405170395900_bib95","doi-asserted-by":"publisher","DOI":"10.1002\/ppp3.70059","article-title":"Leveraging machine learning and citizen science data to describe flowering phenology across South Africa","author":"Stewart","year":"2025","journal-title":"Plants, People, Planet"},{"key":"2026091405170395900_bib96","doi-asserted-by":"publisher","DOI":"10.1145\/964696.964707","article-title":"Automatic thumbnail cropping and its effectiveness","volume-title":"UIST '03: Proceedings of the 16th Annual ACM Symposium on User Interface Software and Technology, 2\u20135 November 2003","author":"Suh","year":"2003"},{"key":"2026091405170395900_bib97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308","article-title":"Rethinking the inception architecture for computer vision","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27\u201330 June 2016","author":"Szegedy","year":"2016"},{"key":"2026091405170395900_bib98","article-title":"Tensorflow Object Detection Model Zoo. Tensorflow","author":"TensorFlow 1 Detection Model Zoo"},{"key":"2026091405170395900_bib99","article-title":"TensorFlow Hub","author":"TensorFlow Hub"},{"key":"2026091405170395900_bib100","article-title":"Tensorflow object detection. Tensorflow","author":"TensorFlow Object Detection API GitHub"},{"key":"2026091405170395900_bib101","doi-asserted-by":"publisher","DOI":"10.1111\/nph.70312","article-title":"On herbarium specimen images and artificial intelligence","author":"Tessler","year":"2025","journal-title":"New Phytologist"},{"key":"2026091405170395900_bib102","unstructured":"Tree of Life Dataset . Tree of Life. Hugging Face. (27 March 2026; https:\/\/huggingface.co\/datasets\/imageomics\/TreeOfLife-10 M)."},{"key":"2026091405170395900_bib103","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1093\/biosci\/biaf042","article-title":"Hespi: A pipeline for automatically detecting information from herbarium specimen sheets","volume":"75","author":"Turnbull","year":"2025","journal-title":"BioScience"},{"key":"2026091405170395900_bib104","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn G, Aodha\u00a0O M, Song Y, Cui Y, Sun C, Shepard A, Adam H, Perona P, Belongie S. 2018. The iNaturalist species classification and detection dataset. IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 18\u201323 June 2018, Salt Lake City, USA. 10.1109\/CVPR.2018.00914","DOI":"10.1109\/CVPR.2018.00914"},{"key":"2026091405170395900_bib105","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn G, Branson S, Farrell R, Haber S, Barry J, Ipeirotis P, Perona P, Belongie S. 2015. Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 7\u201312 June 2015, Boston, USA. 10.1109\/CVPR.2015.7298658","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"2026091405170395900_bib106","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pcbi.1005993","article-title":"Automated plant species identification\u2014Trends and future directions","volume":"14","author":"W\u00e4ldchen","year":"2018","journal-title":"PLoS Computational Biology"},{"key":"2026091405170395900_bib107","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.02696","article-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2022","journal-title":"arXiv"},{"key":"2026091405170395900_bib108","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.251","article-title":"CNN-RNN: A unified framework for multi-label image classification","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 27\u201330 June 2016","author":"Wang","year":"2016"},{"key":"2026091405170395900_bib109","doi-asserted-by":"publisher","first-page":"e16256","DOI":"10.1002\/ajb2.16256","article-title":"Herbarium specimen label transcription reimagined with large language models: Capabilities, productivity, and risks","volume":"110","author":"Weaver","year":"2023","journal-title":"American Journal of Botany"},{"key":"2026091405170395900_bib110","doi-asserted-by":"publisher","first-page":"e11548","DOI":"10.1002\/aps3.11548","article-title":"From leaves to labels: Building modular machine learning networks for rapid herbarium specimen analysis with LeafMachine2","volume":"11","author":"Weaver","year":"2023","journal-title":"Applications in Plant Sciences"},{"key":"2026091405170395900_bib111","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2510.18234","article-title":"DeepSeek-OCR: Contexts optical compression","author":"Wei","year":"2025","journal-title":"arXiv"},{"key":"2026091405170395900_bib112","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TVCG.2019.2934619","article-title":"The what-if tool: Interactive probing of machine learning models","volume":"26","author":"Wexler","year":"2020","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"2026091405170395900_bib113","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1111\/2041-210X.13844","article-title":"Applying computer vision to digitised natural history collections for climate change research: Temperature-size responses in British butterflies","volume":"14","author":"Wilson","year":"2022","journal-title":"Methods in Ecology and Evolution"},{"key":"2026091405170395900_bib114","doi-asserted-by":"publisher","DOI":"10.1111\/nph.70443","article-title":"AI-based identification of Chinese vascular plants from herbarium specimens: A tool for all herbaria with Chinese holdings","author":"Xie","year":"2025","journal-title":"New Phytologist"},{"key":"2026091405170395900_bib115","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.11309","article-title":"Finer-CAM: Spotting the difference reveals finer details for visual explanation","author":"Zhang","year":"2025","journal-title":"arXiv"},{"key":"2026091405170395900_bib116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319","article-title":"Learning deep features for discriminative localization","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 27\u201330 June 2016","author":"Zhou","year":"2016"}],"container-title":["BioScience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioscience\/article-pdf\/76\/9\/813\/70767541\/biag074.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioscience\/article-pdf\/76\/9\/813\/70767541\/biag074.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:17:21Z","timestamp":1789377441000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioscience\/article\/76\/9\/813\/8769063"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"references-count":116,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,8,24]]},"published-print":{"date-parts":[[2026,9,14]]}},"URL":"https:\/\/doi.org\/10.1093\/biosci\/biag074","relation":{},"ISSN":["0006-3568","1525-3244"],"issn-type":[{"value":"0006-3568","type":"print"},{"value":"1525-3244","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,8,24]]}}}