{"id":"https://openalex.org/W4417185231","doi":"https://doi.org/10.1109/iccv51701.2025.00766","title":"Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild","display_name":"Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417185231","doi":"https://doi.org/10.1109/iccv51701.2025.00766"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"letter","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.07759","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100324821","display_name":"Haoran Wang","orcid":"https://orcid.org/0000-0002-1630-4813"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Wang","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100607163","display_name":"Zekun Li","orcid":"https://orcid.org/0000-0002-1207-1901"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zekun Li","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409856","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0001-5486-3125"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667506","display_name":"Lei Qi","orcid":"https://orcid.org/0000-0001-7091-0702"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Qi","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055917015","display_name":"Yinghuan Shi","orcid":"https://orcid.org/0000-0003-4534-7318"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghuan Shi","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]}],"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":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.35910001397132874,"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":0.35910001397132874,"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":0.3244999945163727,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.1298999935388565,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.76419997215271},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.567799985408783},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5475000143051147},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5425999760627747},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5403000116348267},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5347999930381775},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4772999882698059},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.44290000200271606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766000032424927},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.76419997215271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7429999709129333},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6653000116348267},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.567799985408783},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5475000143051147},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5425999760627747},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5403000116348267},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5347999930381775},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4772999882698059},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4300999939441681},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.34470000863075256},{"id":"https://openalex.org/C56435381","wikidata":"https://www.wikidata.org/wiki/Q1196371","display_name":"Geometric transformation","level":3,"score":0.33970001339912415},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C3004257","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Correspondence problem","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.30979999899864197},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2653999924659729}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.07759","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.07759","pdf_url":"https://arxiv.org/pdf/2508.07759","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.07759","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.07759","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.07759","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.07759","pdf_url":"https://arxiv.org/pdf/2508.07759","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6794352704","display_name":null,"funder_award_id":"2024M750424","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"vision":[1,46],"models":[2],"like":[3],"the":[4,18,36,81,95,138,155,162,190],"Segment":[5],"Anything":[6],"Model":[7],"(SAM)":[8],"exhibit":[9],"significant":[10],"limitations":[11],"when":[12],"applied":[13],"to":[14,31,35,113,116,148],"downstream":[15,117],"tasks":[16,118],"in":[17,119,189],"wild.":[19],"Consequently,":[20],"reference":[21,25,50],"segmentation,":[22],"which":[23,57,103],"leverages":[24],"images":[26],"and":[27,64,68],"their":[28],"corresponding":[29],"masks":[30],"impart":[32],"novel":[33,77],"knowledge":[34],"model,":[37],"emerges":[38],"as":[39,88,101],"a":[40,76,89,120,145,150],"promising":[41],"new":[42],"direction":[43],"for":[44,130],"adapting":[45],"models.":[47],"However,":[48],"existing":[49],"segmentation":[51,110,178],"approaches":[52],"predominantly":[53],"rely":[54],"on":[55,174],"meta-learning,":[56],"still":[58],"necessitates":[59],"an":[60],"extensive":[61],"meta-training":[62],"process":[63],"brings":[65],"massive":[66],"data":[67],"computational":[69],"cost.":[70],"In":[71],"this":[72,125,166],"study,":[73],"we":[74],"propose":[75],"approach":[78,126],"by":[79],"representing":[80],"inherent":[82],"correspondence":[83],"between":[84],"reference-target":[85],"image":[86],"pairs":[87],"pseudo":[90],"video.":[91],"This":[92],"perspective":[93],"allows":[94],"latest":[96],"version":[97],"of":[98],"SAM,":[99],"known":[100],"SAM2,":[102],"is":[104,187],"equipped":[105],"with":[106],"interactive":[107],"video":[108],"object":[109],"(iVOS)":[111],"capabilities,":[112],"be":[114],"adapted":[115],"lightweight":[121],"manner.":[122],"We":[123,171],"term":[124],"Correspondence":[127],"As":[128],"Video":[129],"SAM":[131],"(CAV-SAM).":[132],"CAV-SAM":[133],"comprises":[134],"two":[135],"key":[136],"modules:":[137],"Diffusion-Based":[139],"Semantic":[140],"Transition":[141],"(DBST)":[142],"module":[143,160],"employs":[144],"diffusion":[146],"model":[147],"construct":[149],"semantic":[151],"transformation":[152],"sequence,":[153],"while":[154],"Test-Time":[156],"Geometric":[157],"Alignment":[158],"(TTGA)":[159],"aligns":[161],"geometric":[163],"changes":[164],"within":[165],"sequence":[167],"through":[168],"test-time":[169],"fine-tuning.":[170],"evaluated":[172],"CAVSAM":[173],"widely-used":[175],"datasets,":[176],"achieving":[177],"performance":[179],"improvements":[180],"exceeding":[181],"5%":[182],"over":[183],"SOTA":[184],"methods.":[185],"Implementation":[186],"provided":[188],"supplementary":[191],"materials.":[192]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}