{"id":"https://openalex.org/W6929952890","doi":"https://doi.org/10.5281/zenodo.10479317","title":"WildCLIP: Scene and animal attribute retrieval from camera trap data with domain-adapted vision-language models","display_name":"WildCLIP: Scene and animal attribute retrieval from camera trap data with domain-adapted vision-language models","publication_year":2024,"publication_date":"2024-01-19","ids":{"openalex":"https://openalex.org/W6929952890","doi":"https://doi.org/10.5281/zenodo.10479317"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10479317","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10479317","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10479317","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gabeff, Valentin","orcid":"https://orcid.org/0000-0003-3352-1825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabeff, Valentin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3352-1825","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ru\u00dfwurm, Marc","orcid":"https://orcid.org/0000-0001-6612-5744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ru\u00dfwurm, Marc","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6612-5744","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tuia, Devis","orcid":"https://orcid.org/0000-0003-0374-2459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuia, Devis","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0374-2459","affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Mathis, Alexander","orcid":"https://orcid.org/0000-0002-3777-2202"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathis, Alexander","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne"],"raw_orcid":"https://orcid.org/0000-0002-3777-2202","affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10347","display_name":"Atmospheric aerosols and clouds","score":0.4749000072479248,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10347","display_name":"Atmospheric aerosols and clouds","score":0.4749000072479248,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12383","display_name":"Aeolian processes and effects","score":0.051600001752376556,"subfield":{"id":"https://openalex.org/subfields/1904","display_name":"Earth-Surface Processes"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10325","display_name":"Astro and Planetary Science","score":0.048700001090765,"subfield":{"id":"https://openalex.org/subfields/3103","display_name":"Astronomy and Astrophysics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.8361999988555908},{"id":"https://openalex.org/keywords/camera-trap","display_name":"Camera trap","score":0.7023000121116638},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.49869999289512634},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4867999851703644},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.4325000047683716},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.3395000100135803},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.3292999863624573},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.328900009393692}],"concepts":[{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.8361999988555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746999859809875},{"id":"https://openalex.org/C2779101711","wikidata":"https://www.wikidata.org/wiki/Q1723004","display_name":"Camera trap","level":3,"score":0.7023000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011000037193298},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.49869999289512634},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3896999955177307},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.375},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C2985331491","wikidata":"https://www.wikidata.org/wiki/Q5227298","display_name":"Data format","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2513999938964844},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10479317","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10479317","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.10479317","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10479317","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"#############":[0,15],"WildCLIP:":[1],"Scene":[2,361],"and":[3,85,114,191,237,273,329,362,376,379,382,424,427,430,433,436],"animal":[4,363],"attribute":[5,115,364],"retrieval":[6,365],"from":[7,53,265,284,304,324,366],"camera":[8,143,263,277,367,411],"trap":[9,144,368,412],"data":[10,81,112,118,154,213,229,369,400],"with":[11,50,89,134,206,214,222,230,238,282,302,322,370],"domain-adapted":[12,371],"vision-language":[13,64,372],"models":[14,65,102,201,338],"Authors:":[16],"Valentin":[17,375],"Gabeff,":[18],"Marc":[19,378],"Russwurm,":[20,377],"Devis":[21,381],"Tuia":[22],"&":[23],"Alexander":[24],"Mathis":[25],"Affiliation:":[26],"EPFL":[27],"Date:":[28],"January,":[29],"2024":[30],"Link":[31],"to":[32,46,61,83,99,127,235],"the":[33,54,68,77,107,128,152,163,173,179,189,207,223,239,246,250,276,337,345,396],"BiorXiv":[34],"article:":[35,405],"https://www.biorxiv.org/content/10.1101/2023.12.22.572990v1":[36],"--------------------------------":[37],"WildCLIP":[38,93,200],"is":[39,271],"a":[40,135],"fine-tuned":[41],"CLIP":[42,196,204,220],"model":[43,197,205,221],"that":[44],"allows":[45],"retrieve":[47],"camera-trap":[48,72],"events":[49],"natural":[51],"language":[52],"Snapshot":[55,79,132,398],"Serengeti":[56,80,133,399],"dataset.":[57],"This":[58],"project":[59,108],"intends":[60],"demonstrate":[62],"how":[63,98,336],"may":[66],"assist":[67],"annotation":[69],"process":[70],"of":[71,92,120,131,151,175,414],"datasets.":[73],"Here":[74],"we":[75],"provide":[76,245],"processed":[78],"used":[82],"train":[84,251,258],"evaluate":[86],"WildCLIP,":[87],"along":[88],"two":[90],"versions":[91],"(model":[94,198],"weights).":[95],"Details":[96,334],"on":[97,158,212,228,335],"run":[100],"these":[101],"can":[103,155,341],"be":[104,156,342],"found":[105,157,343],"in":[106,344,418],"github":[109],"repository.":[110],"Provided":[111],"(images":[113],"annotations):":[116],"The":[117,257,268],"consists":[119],"380":[121,123],"x":[122],"image":[124],"crops":[125],"corresponding":[126],"MegaDetector":[129,180],"output":[130],"confidence":[136],"threshold":[137],"above":[138],"0.7.":[139],"We":[140,170,243],"considered":[141],"only":[142,295,315],"images":[145,413],"containing":[146,249],"single":[147],"individuals.":[148],"A":[149],"description":[150],"original":[153],"LILA":[159,176,266],"here,":[160],"released":[161],"under":[162],"Community":[164],"Data":[165],"License":[166],"Agreement":[167],"(permissive":[168],"variant).":[169],"warmly":[171],"thank":[172],"authors":[174],"for":[177,187],"making":[178],"outputs":[181],"publicly":[182],"available,":[183],"as":[184,186],"well":[185],"structuring":[188],"dataset":[190],"facilitating":[192],"its":[193],"access.":[194],"Adapted":[195],"weights):":[199],"provided:":[202],"WildCLIP_vitb16_t1.pth:":[203],"ViT-B/16":[208,224],"visual":[209,225],"backbone":[210,226],"trained":[211,227],"captions":[215,231,283,303,323],"following":[216,232],"template":[217,293,313],"1.":[218],"WildCLIP_vitb16_t1t7_lwf.pth:":[219],"templates":[233,285,305,325],"1":[234,286,294,306,314],"7,":[236],"additional":[240],"VR-LwF":[241],"loss.":[242],"also":[244,274,402],"CSV":[247],"files":[248],"/":[252,254,259],"val":[253],"test":[255,260],"splits.":[256],"splits":[261],"follow":[262],"split":[264,270],"(https://lila.science/datasets/snapshot-serengeti).":[267],"validation":[269],"custom,":[272],"at":[275],"level.":[278],"train_dataset_crops_single_animal_template_captions_T1T7_ID.csv:":[279],"Train":[280],"set":[281,301,321],"through":[287,307],"7":[288,308],"(column":[289,296,309,316],"\"all":[290,310,332],"captions\")":[291,311,333],"or":[292,312,355],"\"template":[297,317],"1\")":[298,318],"val_dataset_crops_single_animal_template_captions_T1T7_ID.csv:":[299],"Validation":[300],"test_dataset_crops_single_animal_template_captions_T1T8T10.csv:":[319],"Test":[320],"1,":[326],"8,":[327],"9":[328],"10":[330],"(columns":[331],"were":[339],"generated":[340],"associated":[346],"publication":[347],"(preprint).":[348],"References:":[349],"If":[350,393],"you":[351,394],"find":[352],"our":[353],"code,":[354],"weights,":[356],"please":[357,401],"cite:":[358],"@article{gabeff2023wildclip,":[359],"title={WildCLIP:":[360],"models},":[373],"author={Gabeff,":[374],"Tuia,":[380],"Mathis,":[383],"Alexander},":[384],"journal={bioRxiv},":[385],"pages={2023--12},":[386],"year={2023},":[387],"publisher={Cold":[388],"Spring":[389],"Harbor":[390],"Laboratory}":[391],"}":[392,448],"use":[395],"adapted":[397],"cite":[403],"their":[404],"@article{swanson2015snapshot,":[406],"title={Snapshot":[407],"Serengeti,":[408],"high-frequency":[409],"annotated":[410],"40":[415],"mammalian":[416],"species":[417],"an":[419],"African":[420],"savanna},":[421],"author={Swanson,":[422],"Alexandra":[423],"Kosmala,":[425],"Margaret":[426],"Lintott,":[428],"Chris":[429],"Simpson,":[431],"Robert":[432],"Smith,":[434],"Arfon":[435],"Packer,":[437],"Craig},":[438],"journal={Scientific":[439],"data},":[440],"volume={2},":[441],"number={1},":[442],"pages={1--14},":[443],"year={2015},":[444],"publisher={Nature":[445],"Publishing":[446],"Group}":[447]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}