{"id":"https://openalex.org/W4395111553","doi":"https://doi.org/10.1007/s11263-024-02026-6","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":"2024-04-24","ids":{"openalex":"https://openalex.org/W4395111553","doi":"https://doi.org/10.1007/s11263-024-02026-6"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-024-02026-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-024-02026-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-024-02026-6.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-024-02026-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068584422","display_name":"Valentin Gabeff","orcid":"https://orcid.org/0000-0003-3352-1825"},"institutions":[{"id":"https://openalex.org/I4210097825","display_name":"MIND Research Institute","ror":"https://ror.org/00we1gw23","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210097825"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Valentin Gabeff","raw_affiliation_strings":["Brain Mind and NeuroX Institute, School of Life Sciences, EPFL, Geneva, Switzerland","Environmental Computational Science and Earth Observation Laboratory, EPFL, Sion, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-3352-1825","affiliations":[{"raw_affiliation_string":"Brain Mind and NeuroX Institute, School of Life Sciences, EPFL, Geneva, Switzerland","institution_ids":["https://openalex.org/I4210097825","https://openalex.org/I5124864"]},{"raw_affiliation_string":"Environmental Computational Science and Earth Observation Laboratory, EPFL, Sion, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012237329","display_name":"Marc Ru\u00dfwurm","orcid":"https://orcid.org/0000-0001-6612-5744"},"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"]},{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["CH","NL"],"is_corresponding":false,"raw_author_name":"Marc Ru\u00dfwurm","raw_affiliation_strings":["Environmental Computational Science and Earth Observation Laboratory, EPFL, Sion, Switzerland","Laboratory of Geo-information Science and Remote Sensing, WUR, Wageningen, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-6612-5744","affiliations":[{"raw_affiliation_string":"Environmental Computational Science and Earth Observation Laboratory, EPFL, Sion, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Laboratory of Geo-information Science and Remote Sensing, WUR, Wageningen, The Netherlands","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005192117","display_name":"Devis Tuia","orcid":"https://orcid.org/0000-0003-0374-2459"},"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":true,"raw_author_name":"Devis Tuia","raw_affiliation_strings":["Environmental Computational Science and Earth Observation Laboratory, EPFL, Sion, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-0374-2459","affiliations":[{"raw_affiliation_string":"Environmental Computational Science and Earth Observation Laboratory, EPFL, Sion, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013861606","display_name":"Alexander Mathis","orcid":"https://orcid.org/0000-0002-3777-2202"},"institutions":[{"id":"https://openalex.org/I4210097825","display_name":"MIND Research Institute","ror":"https://ror.org/00we1gw23","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210097825"]},{"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","US"],"is_corresponding":true,"raw_author_name":"Alexander Mathis","raw_affiliation_strings":["Brain Mind and NeuroX Institute, School of Life Sciences, EPFL, Geneva, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-3777-2202","affiliations":[{"raw_affiliation_string":"Brain Mind and NeuroX Institute, School of Life Sciences, EPFL, Geneva, Switzerland","institution_ids":["https://openalex.org/I4210097825","https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005192117","https://openalex.org/A5013861606"],"corresponding_institution_ids":["https://openalex.org/I4210097825","https://openalex.org/I5124864"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":3.2897,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.9359022,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"132","issue":"9","first_page":"3770","last_page":"3786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8386214375495911},{"id":"https://openalex.org/keywords/camera-trap","display_name":"Camera trap","score":0.7874492406845093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5916587114334106},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5815742015838623},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5034336447715759},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4860880672931671},{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.46851396560668945},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4321511387825012},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38597390055656433},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36168134212493896},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2307763695716858},{"id":"https://openalex.org/keywords/wildlife","display_name":"Wildlife","score":0.17804285883903503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8386214375495911},{"id":"https://openalex.org/C2779101711","wikidata":"https://www.wikidata.org/wiki/Q1723004","display_name":"Camera trap","level":3,"score":0.7874492406845093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5916587114334106},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5815742015838623},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5034336447715759},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4860880672931671},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.46851396560668945},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4321511387825012},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38597390055656433},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36168134212493896},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2307763695716858},{"id":"https://openalex.org/C29376679","wikidata":"https://www.wikidata.org/wiki/Q241741","display_name":"Wildlife","level":2,"score":0.17804285883903503},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11263-024-02026-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-024-02026-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-024-02026-6.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},{"id":"pmh:oai:library.wur.nl:wurpubs/629802","is_oa":true,"landing_page_url":"https://research.wur.nl/en/publications/wildclip-scene-and-animal-attribute-retrieval-from-camera-trap-da","pdf_url":"https://edepot.wur.nl/657604","source":{"id":"https://openalex.org/S4210201231","display_name":"Socio-Environmental Systems Modeling","issn_l":"2663-3027","issn":["2663-3027"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 0920-5691","raw_type":"Article/Letter to editor"},{"id":"pmh:oai:infoscience.epfl.ch:310883","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/207764","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"research article"}],"best_oa_location":{"id":"doi:10.1007/s11263-024-02026-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-024-02026-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-024-02026-6.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.6100000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320915","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395111553.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W2055032654","https://openalex.org/W2126194992","https://openalex.org/W2133286915","https://openalex.org/W2413367505","https://openalex.org/W2473930607","https://openalex.org/W2498805680","https://openalex.org/W2560647685","https://openalex.org/W2563540059","https://openalex.org/W2700797120","https://openalex.org/W2769210209","https://openalex.org/W2810030371","https://openalex.org/W2895082331","https://openalex.org/W2950100524","https://openalex.org/W2952113774","https://openalex.org/W2966715458","https://openalex.org/W2981852735","https://openalex.org/W2999905431","https://openalex.org/W3009074285","https://openalex.org/W3088087146","https://openalex.org/W3088235422","https://openalex.org/W3093414036","https://openalex.org/W3126202038","https://openalex.org/W3131523960","https://openalex.org/W3134630366","https://openalex.org/W3158371937","https://openalex.org/W4210595379","https://openalex.org/W4210883322","https://openalex.org/W4210926750","https://openalex.org/W4220760426","https://openalex.org/W4225323055","https://openalex.org/W4226278401","https://openalex.org/W4304699759","https://openalex.org/W4323240715","https://openalex.org/W4361866031","https://openalex.org/W4384111647","https://openalex.org/W4385573131","https://openalex.org/W4386790226","https://openalex.org/W4390872747","https://openalex.org/W6739901393","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2361861616","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2263699433"],"abstract_inverted_index":{"Abstract":[0],"Wildlife":[1],"observation":[2],"with":[3,104,204],"camera":[4,23],"traps":[5,24],"has":[6],"great":[7,90],"potential":[8,135],"for":[9],"ethology":[10],"and":[11,52,70,114,120,144,157,182,206],"ecology,":[12],"as":[13,83],"it":[14,185],"gathers":[15],"data":[16,41,76],"non-invasively":[17],"in":[18,74,174,190],"an":[19,165],"automated":[20],"way.":[21],"However,":[22],"produce":[25],"large":[26,75],"amounts":[27],"of":[28,49,65,97,109,136],"uncurated":[29],"data,":[30],"which":[31],"is":[32,111,211],"time-consuming":[33],"to":[34,38,59,72,92,125,138,142,158,168,171,200],"annotate.":[35],"Existing":[36],"methods":[37],"label":[39],"these":[40],"automatically":[42],"commonly":[43],"use":[44],"a":[45,175],"fixed":[46,113],"pre-defined":[47],"set":[48,108],"distinctive":[50],"classes":[51,110],"require":[53],"many":[54],"labeled":[55],"examples":[56],"per":[57],"class":[58],"be":[60,102,116],"trained.":[61],"Moreover,":[62],"the":[63,94,107,134,191],"attributes":[64,173,189],"interest":[66],"are":[67],"sometimes":[68],"rare":[69,127],"difficult":[71],"find":[73],"collections.":[77],"Large":[78],"pretrained":[79,121],"vision-language":[80],"models,":[81],"such":[82],"contrastive":[84],"language":[85],"image":[86],"pretraining":[87],"(CLIP),":[88],"offer":[89],"promises":[91],"facilitate":[93,201],"annotation":[95,202],"process":[96],"camera-trap":[98,155],"data.":[99],"Images":[100],"can":[101,115,123,186],"described":[103],"greater":[105],"detail,":[106],"not":[112],"extensible":[117],"on":[118,153],"demand":[119],"models":[122],"help":[124],"retrieve":[126,139,187],"samples.":[128],"In":[129],"this":[130],"work,":[131],"we":[132,163],"explore":[133],"CLIP":[137,152],"images":[140,156],"according":[141],"environmental":[143],"ecological":[145],"attributes.":[146],"We":[147,178],"create":[148],"WildCLIP":[149],"by":[150],"fine-tuning":[151],"wildlife":[154],"further":[159],"increase":[160],"its":[161],"flexibility,":[162],"add":[164],"adapter":[166],"module":[167],"better":[169],"expand":[170],"novel":[172,188],"few-shot":[176],"manner.":[177],"quantify":[179],"WildCLIP\u2019s":[180],"performance":[181],"show":[183],"that":[184],"Snapshot":[192],"Serengeti":[193],"dataset.":[194],"Our":[195],"findings":[196],"outline":[197],"new":[198],"opportunities":[199],"processes":[203],"complex":[205],"multi-attribute":[207],"captions.":[208],"The":[209],"code":[210],"available":[212],"at":[213],"https://github.com/amathislab/wildclip":[214],".":[215]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":11}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}