{"id":"https://openalex.org/W7140323570","doi":"https://doi.org/10.48550/arxiv.2603.23030","title":"Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation","display_name":"Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7140323570","doi":"https://doi.org/10.48550/arxiv.2603.23030"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.23030","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23030","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.23030","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021852893","display_name":"Byeongcheol Lee","orcid":"https://orcid.org/0000-0001-7076-5752"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, ByeongCheol","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027197815","display_name":"Hyun Seok Seong","orcid":"https://orcid.org/0000-0002-7952-2017"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seong, Hyun Seok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130593573","display_name":"Sangeek Hyun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyun, Sangeek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130614858","display_name":"Gilhan Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Gilhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130601713","display_name":"WonJun Moon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moon, WonJun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130566779","display_name":"Jae-Pil Heo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heo, Jae-Pil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5756000280380249,"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":0.5756000280380249,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.21320000290870667,"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":0.04340000078082085,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6480000019073486},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6370999813079834},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42989999055862427},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.41819998621940613},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.40290001034736633},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.3666999936103821},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3465000092983246},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.34150001406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8508999943733215},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6480000019073486},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6370999813079834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827000141143799},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42989999055862427},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.40290001034736633},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3075999915599823},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29910001158714294},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.23030","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23030","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2603.23030","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23030","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5667380094528198}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"A":[0],"sliding-window":[1],"inference":[2],"strategy":[3],"is":[4,33,206],"commonly":[5],"adopted":[6],"in":[7,20,198],"recent":[8],"training-free":[9,200],"open-vocabulary":[10,201],"semantic":[11,38,108,139,202],"segmentation":[12,203],"methods":[13,185],"to":[14,37,64,73,91,128,162,173],"overcome":[15],"limitation":[16],"of":[17,196],"the":[18,102,129,170,194],"CLIP":[19],"processing":[21],"high-resolution":[22],"images.":[23],"However,":[24],"this":[25,44],"approach":[26],"introduces":[27],"a":[28,51,83,119,137,153],"new":[29],"challenge:":[30],"each":[31],"window":[32,84,104],"processed":[34],"independently,":[35],"leading":[36],"discrepancy":[39],"across":[40,58,144],"windows.":[41,59,79],"To":[42,114],"address":[43],"issue,":[45],"we":[46,81,117,151],"propose":[47,152],"Global-Local":[48],"Aligned":[49],"CLIP~(GLA-CLIP),":[50],"framework":[52],"that":[53,157],"facilitates":[54],"comprehensive":[55],"information":[56],"exchange":[57],"Rather":[60],"than":[61],"limiting":[62],"attention":[63,159,171],"tokens":[65,72,87,125],"within":[66,101],"individual":[67],"windows,":[68,134],"GLA-CLIP":[69,179,197],"extends":[70],"key-value":[71],"incorporate":[74],"contextual":[75],"cues":[76],"from":[77,132],"all":[78,133],"Nevertheless,":[80],"observe":[82],"bias:":[85],"outer-window":[86,148],"are":[88,97],"less":[89],"likely":[90],"be":[92,181],"attended,":[93],"since":[94],"query":[95,131],"features":[96],"produced":[98],"through":[99],"interactions":[100],"inner":[103],"patches,":[105],"thereby":[106],"lacking":[107],"grounding":[109],"beyond":[110],"their":[111,188],"local":[112],"context.":[113],"mitigate":[115],"this,":[116],"introduce":[118],"proxy":[120],"anchor,":[121],"constructed":[122],"by":[123,165],"aggregating":[124],"highly":[126],"similar":[127],"given":[130],"which":[135],"provides":[136],"unified":[138],"reference":[140],"for":[141],"measuring":[142],"similarity":[143],"both":[145],"inner-":[146],"and":[147,168,186],"patches.":[149],"Furthermore,":[150],"dynamic":[154],"normalization":[155],"scheme":[156],"adjusts":[158],"strength":[160],"according":[161],"object":[163],"scale":[164],"dynamically":[166],"scaling":[167],"thresholding":[169],"map":[172],"cope":[174],"with":[175],"small-object":[176],"scenarios.":[177],"Moreover,":[178],"can":[180],"equipped":[182],"on":[183],"existing":[184],"broad":[187],"receptive":[189],"field.":[190],"Extensive":[191],"experiments":[192],"validate":[193],"effectiveness":[195],"enhancing":[199],"performance.":[204],"Code":[205],"available":[207],"at":[208],"https://github.com/2btlFe/GLA-CLIP.":[209]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-26T00:00:00"}