{"id":"https://openalex.org/W4407632017","doi":"https://doi.org/10.1109/iccv51701.2025.02090","title":"Towards Fine-Grained Interactive Segmentation in Images and Videos","display_name":"Towards Fine-Grained Interactive Segmentation in Images and Videos","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4407632017","doi":"https://doi.org/10.1109/iccv51701.2025.02090"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02090","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.09660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020423887","display_name":"Yuan Yao","orcid":"https://orcid.org/0000-0003-3302-4909"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Yuan Yao","raw_affiliation_strings":["Alibaba Group,Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110380351","display_name":"Qiushi Yang","orcid":"https://orcid.org/0000-0001-5737-5653"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Qiushi Yang","raw_affiliation_strings":["Alibaba Group,Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564882","display_name":"Miaomiao Cui","orcid":"https://orcid.org/0000-0001-5546-3967"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Miaomiao Cui","raw_affiliation_strings":["Alibaba Group,Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085032007","display_name":"Liefeng Bo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Liefeng Bo","raw_affiliation_strings":["Alibaba Group,Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020423887"],"corresponding_institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":1.0652,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74099704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"22509","last_page":"22518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9584000110626221,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9584000110626221,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9419999718666077,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9388999938964844,"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":0.6451600790023804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5893505811691284},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5576808452606201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5138731002807617},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4644833207130432}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6451600790023804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5893505811691284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5576808452606201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5138731002807617},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4644833207130432}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02090","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:2502.09660","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.09660","pdf_url":"https://arxiv.org/pdf/2502.09660","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.09660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.09660","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.09660","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.09660","pdf_url":"https://arxiv.org/pdf/2502.09660","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0],"recent":[1],"Segment":[2],"Anything":[3],"Models":[4],"(SAMs)":[5],"have":[6],"emerged":[7],"as":[8],"foundational":[9,60],"visual":[10],"models":[11],"for":[12,33,85,199],"general":[13],"interactive":[14,35],"segmentation.":[15],"Despite":[16],"demonstrating":[17],"robust":[18],"generalization":[19],"abilities,":[20],"they":[21],"still":[22],"suffer":[23],"performance":[24],"degradations":[25],"in":[26],"scenarios":[27],"demanding":[28],"accurate":[29,154],"masks.":[30],"Existing":[31],"methods":[32],"high-precision":[34],"segmentation":[36,61,83,157],"face":[37],"a":[38,98,112,137,159,167],"trade-off":[39],"between":[40],"the":[41,55,73,127,131,143,179,184,191],"ability":[42,129],"to":[43,80,107,125,141,152,171],"perceive":[44],"intricate":[45],"local":[46,104],"details":[47],"and":[48,57,88,120,202],"maintaining":[49,121],"stable":[50],"prompting":[51,128],"capability,":[52],"which":[53,102],"hinders":[54],"applicability":[56],"effectiveness":[58,185],"of":[59,186],"models.":[62],"To":[63],"this":[64],"end,":[65],"we":[66,96,135],"present":[67],"an":[68],"SAM2Refiner":[69],"framework":[70],"built":[71],"upon":[72],"SAM2":[74,79],"backbone.":[75],"This":[76],"architecture":[77],"allows":[78],"generate":[81],"fine-grained":[82],"masks":[84,198],"both":[86,200],"images":[87,201],"videos":[89],"while":[90],"preserving":[91],"its":[92],"inherent":[93],"strengths.":[94],"Specifically,":[95],"design":[97],"localization":[99],"augment":[100],"module,":[101],"incorporates":[103],"contextual":[105],"cues":[106],"enhance":[108],"global":[109],"features":[110,174],"via":[111],"cross-attention":[113],"mechanism,":[114],"thereby":[115],"exploiting":[116],"potential":[117],"detailed":[118],"patterns":[119],"semantic":[122],"information.":[123],"Moreover,":[124],"strengthen":[126],"toward":[130],"enhanced":[132],"object":[133],"embedding,":[134],"introduce":[136],"prompt":[138,148],"retargeting":[139],"module":[140,162],"renew":[142],"embedding":[144],"with":[145,175],"spatially":[146],"aligned":[147],"features.":[149],"In":[150],"addition,":[151],"obtain":[153],"high":[155],"resolution":[156],"masks,":[158],"mask":[160,173],"refinement":[161],"is":[163],"devised":[164],"by":[165],"employing":[166],"multi-scale":[168],"cascaded":[169],"structure":[170],"fuse":[172],"hierarchical":[176],"representations":[177],"from":[178],"encoder.":[180],"Extensive":[181],"experiments":[182],"demonstrate":[183],"our":[187],"approach,":[188],"revealing":[189],"that":[190],"proposed":[192],"method":[193],"can":[194],"produce":[195],"highly":[196],"precise":[197],"videos,":[203],"surpassing":[204],"state-of-the-art":[205],"methods.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}