{"id":"https://openalex.org/W4411458558","doi":"https://doi.org/10.1007/s44267-025-00082-1","title":"When SAM2 meets video camouflaged object segmentation: a comprehensive evaluation and adaptation","display_name":"When SAM2 meets video camouflaged object segmentation: a comprehensive evaluation and adaptation","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411458558","doi":"https://doi.org/10.1007/s44267-025-00082-1"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-025-00082-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00082-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00082-1.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"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":"Visual Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00082-1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008444914","display_name":"Yuli Zhou","orcid":"https://orcid.org/0000-0003-4584-1893"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yuli Zhou","raw_affiliation_strings":["Computer Vision Laboratory, ETH Z\u00fcrich, Sternwartstrasse 7, 8092, Z\u00fcrich, Switzerland","Department of Informatics, University of Z\u00fcrich, Binzm\u00fchlestrasse 14, 8050, Z\u00fcrich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-4584-1893","affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, ETH Z\u00fcrich, Sternwartstrasse 7, 8092, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Informatics, University of Z\u00fcrich, Binzm\u00fchlestrasse 14, 8050, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010215983","display_name":"Guolei Sun","orcid":"https://orcid.org/0000-0001-8667-9656"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Guolei Sun","raw_affiliation_strings":["Computer Vision Laboratory, ETH Z\u00fcrich, Sternwartstrasse 7, 8092, Z\u00fcrich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-8667-9656","affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, ETH Z\u00fcrich, Sternwartstrasse 7, 8092, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377386","display_name":"Yawei Li","orcid":"https://orcid.org/0000-0002-8948-7892"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yawei Li","raw_affiliation_strings":["Computer Vision Laboratory, ETH Z\u00fcrich, Sternwartstrasse 7, 8092, Z\u00fcrich, Switzerland","Integrated System Laboratory, ETH Z\u00fcrich, Gloriastrasse 35, 8092, Z\u00fcrich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-8948-7892","affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, ETH Z\u00fcrich, Sternwartstrasse 7, 8092, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Integrated System Laboratory, ETH Z\u00fcrich, Gloriastrasse 35, 8092, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084688255","display_name":"Guo-Sen Xie","orcid":"https://orcid.org/0000-0002-5487-9845"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo-Sen Xie","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China"],"raw_orcid":"https://orcid.org/0000-0002-5487-9845","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043408422","display_name":"Luca Benini","orcid":"https://orcid.org/0000-0001-8068-3806"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["CH","IT"],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["Department of Electrical, Electronic, and Information Engineering, University of Bologna, Via Zamboni 33, Bologna, 40126, Bologna, Italy","Integrated System Laboratory, ETH Z\u00fcrich, Gloriastrasse 35, 8092, Z\u00fcrich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-8068-3806","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronic, and Information Engineering, University of Bologna, Via Zamboni 33, Bologna, 40126, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"Integrated System Laboratory, ETH Z\u00fcrich, Gloriastrasse 35, 8092, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036970822","display_name":"Ender Konuko\u011flu","orcid":"https://orcid.org/0000-0002-2542-3611"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ender Konukoglu","raw_affiliation_strings":["Computer Vision Laboratory, ETH Z\u00fcrich, Sternwartstrasse 7, 8092, Z\u00fcrich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-2542-3611","affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, ETH Z\u00fcrich, Sternwartstrasse 7, 8092, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010215983"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":5.0539,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.95970984,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"3","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9991000294685364,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9991000294685364,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.949999988079071,"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/T10971","display_name":"Olfactory and Sensory Function Studies","score":0.923799991607666,"subfield":{"id":"https://openalex.org/subfields/2809","display_name":"Sensory Systems"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.801865816116333},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7232654094696045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6201000809669495},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5818825364112854},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5794289708137512},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5612028241157532},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.560039758682251},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08526909351348877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.801865816116333},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7232654094696045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6201000809669495},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5818825364112854},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5794289708137512},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5612028241157532},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.560039758682251},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08526909351348877},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s44267-025-00082-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00082-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00082-1.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"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":"Visual Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:cris.unibo.it:11585/1039444","is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/1039444","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:0a9ae9b22764400b8ec8e6a6caffd80b","is_oa":true,"landing_page_url":"https://doaj.org/article/0a9ae9b22764400b8ec8e6a6caffd80b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Visual Intelligence, Vol 3, Iss 1, Pp 1-14 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44267-025-00082-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00082-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00082-1.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"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":"Visual Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411458558.pdf","grobid_xml":"https://content.openalex.org/works/W4411458558.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W1982075130","https://openalex.org/W2326050853","https://openalex.org/W2531563875","https://openalex.org/W2602856279","https://openalex.org/W2740248187","https://openalex.org/W2804610335","https://openalex.org/W2913935484","https://openalex.org/W2914304175","https://openalex.org/W2937549930","https://openalex.org/W2966953718","https://openalex.org/W2969502377","https://openalex.org/W3035811871","https://openalex.org/W3108460979","https://openalex.org/W3133947967","https://openalex.org/W3152836006","https://openalex.org/W3160957808","https://openalex.org/W3164098653","https://openalex.org/W3212593512","https://openalex.org/W4221151441","https://openalex.org/W4236965008","https://openalex.org/W4284895289","https://openalex.org/W4301409532","https://openalex.org/W4389115526","https://openalex.org/W4391697007","https://openalex.org/W4394699010","https://openalex.org/W4394730072","https://openalex.org/W4394972273","https://openalex.org/W4398202893","https://openalex.org/W4399555151","https://openalex.org/W4399923948","https://openalex.org/W4401475400","https://openalex.org/W4402727860","https://openalex.org/W4402951577","https://openalex.org/W4403420280","https://openalex.org/W4403791683","https://openalex.org/W4404001948","https://openalex.org/W4404654755","https://openalex.org/W4406657538","https://openalex.org/W4409224394","https://openalex.org/W6674505857","https://openalex.org/W6735463952","https://openalex.org/W6757817989","https://openalex.org/W6765841262","https://openalex.org/W6851578965","https://openalex.org/W6851592950","https://openalex.org/W6852054059","https://openalex.org/W6856279490"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1526712007","https://openalex.org/W1533421371","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2732813147","https://openalex.org/W2143460112","https://openalex.org/W2042906257"],"abstract_inverted_index":{"Abstract":[0],"This":[1,82],"study":[2,83,87],"investigates":[3],"the":[4,9,16,33,49,114,137,148],"application":[5],"and":[6,41,43,105,109,125],"performance":[7,97],"of":[8,19,116],"Segment":[10],"Anything":[11],"Model":[12],"2":[13],"(SAM2)":[14],"in":[15,32,51,70,76,91,156],"challenging":[17],"task":[18],"video":[20,64,100,138],"camouflaged":[21,54,78,99,139,154],"object":[22],"segmentation":[23],"(VCOS).":[24],"VCOS":[25,126],"involves":[26],"detecting":[27],"objects":[28,50,55,155],"that":[29,145,161],"blend":[30],"seamlessly":[31],"surroundings":[34],"for":[35,173],"videos":[36],"due":[37],"to":[38,48,60,152],"similar":[39],"colors":[40],"textures":[42],"poor":[44],"light":[45],"conditions.":[46],"Compared":[47],"normal":[52],"scenes,":[53],"are":[56],"much":[57],"more":[58],"difficult":[59],"detect.":[61],"SAM2,":[62],"a":[63,85],"foundation":[65],"model,":[66],"has":[67,147],"shown":[68],"potential":[69],"various":[71],"tasks.":[72],"However,":[73],"its":[74],"effectiveness":[75],"dynamic":[77],"scenarios":[79],"remains":[80],"under-explored.":[81],"presents":[84],"comprehensive":[86,142],"on":[88,98,136],"SAM2\u2019s":[89,96,171],"ability":[90,151,163],"VCOS.":[92,174],"First,":[93],"we":[94,112,129],"assess":[95],"datasets":[101],"using":[102],"different":[103],"models":[104,123],"prompts":[106],"(click,":[107],"box,":[108],"mask).":[110],"Second,":[111],"explore":[113],"integration":[115],"SAM2":[117,132,146],"with":[118],"existing":[119],"multimodal":[120],"large":[121],"language":[122],"(MLLMs)":[124],"methods.":[127],"Third,":[128],"specifically":[130,169],"adapt":[131],"by":[133,168],"fine-tuning":[134],"it":[135],"dataset.":[140],"Our":[141],"experiments":[143],"demonstrate":[144],"excellent":[149],"zero-shot":[150],"detect":[153],"videos.":[157],"We":[158],"also":[159],"show":[160],"this":[162],"could":[164],"be":[165],"further":[166],"improved":[167],"adjusting":[170],"parameters":[172]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
