[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82354-en":3,"doc-seo-82354-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82354,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Parameter-Efficient Vision Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification","Long-term animal re-identification (ReID) requires models to stay reliable despite gradual morphological change and seasonal appearance shifts, which also create identity and temporal distribution mismatches. The work introduces a parameter-efficient adaptation of CLIP for animal ReID and a continuous metadata-conditioning method that injects numerical attributes directly into prompt representations during training. Low-rank visual adaptation and cross-modal alignment support training, while experiments on a seven-year fish dataset and wildlife benchmarks validate gains in closed-set, open-set, and time-aware evaluations.","Parameter-Efficient Vision–Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification⋆  \nAnil Osman Tura , Tonje Knutsen Sørdalenb,c , Kim Tallaksen Halvorsenb and Cigdem Beyana,∗  \na Department of Computer Science, University of Verona, Verona, 37134, Italy b Institute of Marine Research, Nye Flødevigveien 20, 4817 His, Norway c University of Agder, Centre for Coastal Research, Grimstad, 4604, Norway  \narXiv :2607 .09443v1 [ cs .CV] 10 Jul 2026  \nARTICLE INFO  \nKeywords:  \nAnimal Re-Identification Vision–Language Models Prompt Learning  \nLow-Rank Adaptation Continuous Metadata Conditioning Longitudinal Evaluation  \nAB STRACT  \nLong-term animal re-identification (ReID) must remain robust to gradual morphological evolution and seasonal appearance shifts. Although recent vision–language models provide strong pretrained visual representations, adapting them to longitudinal ecological settings remains challenging, particularly under identity and temporal distribution shifts. We present a parameter-efficient CLIP adaptation framework for animal ReID and introduce a continuous metadata-conditioning mechanism that incorporates numerical attributes directly into the prompt representation during training. While lowrank visual adaptation, prompt-based supervision, and cross-modal alignment provide the adaptation framework, the proposed metadata-conditioning strategy constitutes the primary methodological contribution. By preserving the continuous structure of numerical metadata rather than discretizing it into textual categories, the proposed approach enables smooth modulation of the embedding space during training while maintaining a purely visual inference pipeline. Experiments on a seven-year longitudinal fish dataset and multiple wildlife benchmarks demonstrate improved performance under closed-set, open-set, and time-aware evaluation protocols. The results demonstrate that continuous metadata conditioning improves robustness to longitudinal appearance variation and temporal distribution shifts, while parameter-efficient adaptation enables a purely visual inference pipeline without requiring metadata at test time. Code and evaluation splits can be found at: [https://github.com/](https://github.com/)[ ](https://github.com/)AnilOsmanTur/MetaPrompt-ReID.  \nAuthor’s Note. This is the author’s accepted manuscript of the paper accepted for publication in Expert Systems with Applications. The final authenticated version will be available from the publisher.  \n1. Introduction  \nAnimal re-identification (ReID) refers to the recognition of previously observed individuals across time and has long been an important component of wildlife population monitoring, capture–recapture studies, and behavioral ecology [34] . In computer vision, the term more specifically denotes identifying individual animals from images or video sequences without the use of invasive tagging. Automated visual ReID enables large-scale longitudinal tracking under natural conditions [17, 9, 31]; however, this requires models to learn identity-discriminative representations capable of matching individuals across encounters based solely on visual appearance as it changes over time [40, 50, 27, 3] .  \nUnlike person or vehicle ReID, animal ReID frequently involves long-term re-observation, where the same individual may be encountered months or even years apart [1, 39, 2] . This setting introduces challenges beyond viewpoint  \n⋆  \n∗ Corresponding author. Email: [cigdem.beyan@univr.it](cigdem.beyan@univr.it)  \n [anilosman.tur@univr.it](anilosman.tur@univr.it) (A.O. Tur); [tonje.sordalen@hi.no](tonje.sordalen@hi.no) (T.K. Sørdalen); [kim.halvorsen@hi.no](kim.halvorsen@hi.no) (K.T. Halvorsen); [cigdem.beyan@univr.it](cigdem.beyan@univr.it)[ ](cigdem.beyan@univr.it)(C. Beyan)  \nORCID(s): 0000-0001-7772-5235 (A.O. Tur); 0000-0001-5836-9327 (T.K. Sørdalen); 0000-0001-6857-2492 (K.T. Halvorsen);  \n0000-0002-9583-0087 (C. Beyan)  \nand illumination variation. ","cbCaioFh6MO4wOcA","https://ap.wps.com/l/cbCaioFh6MO4wOcA","pdf",13634294,1,24,"English","en",105,"# Introduction\n## Long-term animal Re-Identification challenges\n## Fish ReID and the Melops dataset\n## Vision–language models for ReID","[{\"question\":\"What problem does the document address in animal re-identification?\",\"answer\":\"It addresses the need for robust long-term animal ReID under gradual morphological evolution and seasonal appearance changes, which cause identity and temporal distribution shifts.\"},{\"question\":\"How does the proposed method incorporate metadata during training?\",\"answer\":\"It uses continuous metadata-conditioning that feeds numerical attributes directly into the prompt representation, preserving numerical structure instead of discretizing into text categories.\"},{\"question\":\"What evidence is used to evaluate the approach?\",\"answer\":\"Experiments are conducted on a seven-year longitudinal fish dataset (Melops) and multiple wildlife benchmarks, evaluated under closed-set, open-set, and time-aware protocols.\"}]",1784179837,60,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"parameter-efficient-vision-language-adaptation-with-continuous-metadata-conditioning-for-animal-re-identification","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/parameter-efficient-vision-language-adaptation-with-continuous-metadata-conditioning-for-animal-re-identification/82354/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the document address in animal re-identification?","Question",{"text":75,"@type":76},"It addresses the need for robust long-term animal ReID under gradual morphological evolution and seasonal appearance changes, which cause identity and temporal distribution shifts.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method incorporate metadata during training?",{"text":80,"@type":76},"It uses continuous metadata-conditioning that feeds numerical attributes directly into the prompt representation, preserving numerical structure instead of discretizing into text categories.",{"name":82,"@type":73,"acceptedAnswer":83},"What evidence is used to evaluate the approach?",{"text":84,"@type":76},"Experiments are conducted on a seven-year longitudinal fish dataset (Melops) and multiple wildlife benchmarks, evaluated under closed-set, open-set, and time-aware protocols.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":28,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]