{"id":"https://openalex.org/W4403792258","doi":"https://doi.org/10.1145/3664647.3680989","title":"One-shot In-context Part Segmentation","display_name":"One-shot In-context Part Segmentation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792258","doi":"https://doi.org/10.1145/3664647.3680989"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680989","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.01144","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhenqi Dai","orcid":"https://orcid.org/0009-0005-0497-9118"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenqi Dai","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0005-0497-9118","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057382261","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0003-3458-6567"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-3458-6567","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343569","display_name":"Xingxing Zhang","orcid":"https://orcid.org/0000-0003-4012-3796"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingxing Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4012-3796","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087043856","display_name":"Yunchao Wei","orcid":"https://orcid.org/0000-0002-2812-8781"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunchao Wei","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2812-8781","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028235866","display_name":"Yanning Zhang","orcid":"https://orcid.org/0000-0002-2977-8057"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanning Zhang","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-2977-8057","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2069,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50039092,"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":"10966","last_page":"10975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9987000226974487,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9904000163078308,"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/shot","display_name":"Shot (pellet)","score":0.7698554992675781},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6545970439910889},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.624301552772522},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5758188962936401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4877949059009552},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.41159260272979736},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3603235185146332},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.15965065360069275},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.05541473627090454}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7698554992675781},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6545970439910889},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.624301552772522},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5758188962936401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4877949059009552},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41159260272979736},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3603235185146332},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.15965065360069275},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.05541473627090454},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680989","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.01144","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.01144","pdf_url":"https://arxiv.org/pdf/2503.01144","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.01144","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.01144","pdf_url":"https://arxiv.org/pdf/2503.01144","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W1903370114","https://openalex.org/W2104408738","https://openalex.org/W2254462240","https://openalex.org/W2309415944","https://openalex.org/W2412782625","https://openalex.org/W2963935758","https://openalex.org/W2964252655","https://openalex.org/W2990138404","https://openalex.org/W2995888011","https://openalex.org/W3034521057","https://openalex.org/W3035524453","https://openalex.org/W3159481202","https://openalex.org/W3167788848","https://openalex.org/W3173143063","https://openalex.org/W4294495258","https://openalex.org/W4312815172","https://openalex.org/W4312933868","https://openalex.org/W4312956471","https://openalex.org/W4313156423","https://openalex.org/W4382459155","https://openalex.org/W4386075591","https://openalex.org/W4386076333","https://openalex.org/W4387323307","https://openalex.org/W4388191449","https://openalex.org/W4388191728","https://openalex.org/W4390871819","https://openalex.org/W4390872642","https://openalex.org/W4390874575","https://openalex.org/W4393184662"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W1522196789"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,125,191],"present":[4],"the":[5,15,42,57,60,71,80,115,134,145,149,153,172,194],"One-shot":[6],"In-context":[7],"Part":[8],"Segmentation":[9],"(OIParts)":[10],"framework,":[11],"designed":[12],"to":[13,76,90],"tackle":[14],"challenges":[16],"of":[17,118,148,196],"part":[18,29,91,202],"segmentation":[19,30,92,107,160,203],"by":[20,132],"leveraging":[21],"visual":[22],"foundation":[23],"models":[24],"(VFMs).":[25],"Existing":[26],"training-based":[27],"one-shot":[28,43,72,206],"methods":[31],"that":[32,68,93],"utilize":[33],"VFMs":[34],"encounter":[35],"difficulties":[36],"when":[37,56],"faced":[38],"with":[39,108],"scenarios":[40],"where":[41],"image":[44,47,62],"and":[45,53,97,122],"test":[46,61],"exhibit":[48],"significant":[49],"variance":[50],"in":[51,59,205],"appearance":[52],"perspective,":[54],"or":[55],"object":[58,164],"is":[63,94],"partially":[64],"visible.":[65],"We":[66,156],"argue":[67],"training":[69],"on":[70,187],"example":[73,104],"often":[74],"leads":[75],"overfitting,":[77],"thereby":[78,143],"compromising":[79],"model's":[81],"generalization":[82,110,182],"capability.":[83],"Our":[84],"framework":[85,168],"offers":[86],"a":[87,101],"novel":[88],"approach":[89,131],"training-free,":[95],"flexible,":[96],"data-efficient,":[98],"requiring":[99],"only":[100,170],"single":[102],"in-context":[103],"for":[105,137,152,174],"precise":[106],"superior":[109,181],"ability.":[111,183],"By":[112],"thoroughly":[113],"exploring":[114],"complementary":[116],"strengths":[117],"VFMs,":[119],"specifically":[120],"DINOv2":[121],"Stable":[123],"Diffusion,":[124],"introduce":[126],"an":[127],"adaptive":[128],"channel":[129],"selection":[130],"minimizing":[133],"intra-class":[135],"distance":[136],"better":[138],"exploiting":[139],"these":[140],"two":[141],"features,":[142],"enhancing":[144],"discriminatory":[146],"power":[147],"extracted":[150],"features":[151],"fine-grained":[154],"parts.":[155],"have":[157,192],"achieved":[158],"remarkable":[159],"performance":[161],"across":[162],"diverse":[163],"categories.":[165],"The":[166],"OIParts":[167],"not":[169],"eliminates":[171],"need":[173],"extensive":[175],"labeled":[176],"data":[177],"but":[178],"also":[179],"demonstrates":[180],"Through":[184],"comprehensive":[185],"experimentation":[186],"three":[188],"benchmark":[189],"datasets,":[190],"demonstrated":[193],"superiority":[195],"our":[197],"proposed":[198],"method":[199],"over":[200],"existing":[201],"approaches":[204],"settings.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}