{"id":"https://openalex.org/W7131070903","doi":"https://doi.org/10.1109/access.2026.3667444","title":"CGSeg: Cross-Aggregation and Gated Fusion for Open-Vocabulary Semantic Segmentation","display_name":"CGSeg: Cross-Aggregation and Gated Fusion for Open-Vocabulary Semantic Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131070903","doi":"https://doi.org/10.1109/access.2026.3667444"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3667444","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3667444","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3667444","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091239059","display_name":"Zhengyu Xia","orcid":"https://orcid.org/0000-0001-5225-5580"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhengyu Xia","raw_affiliation_strings":["Illinois Institute of Technology (Illinois Tech), Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology (Illinois Tech), Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076689613","display_name":"Joohee Kim","orcid":"https://orcid.org/0000-0001-8833-0319"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joohee Kim","raw_affiliation_strings":["Illinois Institute of Technology (Illinois Tech), Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology (Illinois Tech), Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091239059"],"corresponding_institution_ids":["https://openalex.org/I180949307"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79890997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"30812","last_page":"30829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7538999915122986,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7538999915122986,"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/T10028","display_name":"Topic Modeling","score":0.08139999955892563,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0284000001847744,"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/pascal","display_name":"Pascal (unit)","score":0.8373000025749207},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7620999813079834},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5939000248908997},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5098999738693237},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5002999901771545},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45350000262260437},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.45210000872612},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41920000314712524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633999824523926},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.8373000025749207},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7620999813079834},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5939000248908997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5321000218391418},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5098999738693237},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5002999901771545},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.38960000872612},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.37929999828338623},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.35659998655319214},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.349700003862381},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34450000524520874},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.328000009059906},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.31850001215934753},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.26489999890327454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3667444","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3667444","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3667444","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3667444","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47371870279312134}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"semantic":[1],"segmentation":[2,154,164],"(OVSS)":[3],"aims":[4],"to":[5,107],"segment":[6],"arbitrary":[7],"categories":[8],"specified":[9],"by":[10,13,31],"text":[11,53,114],"prompts":[12],"leveraging":[14],"the":[15,56,73,144,149,187],"rich":[16],"visual-language":[17],"knowledge":[18],"of":[19,186],"pretrained":[20],"vision-language":[21],"models":[22],"(VLMs).":[23],"Recent":[24],"one-stage,":[25],"cost-based":[26,88],"approaches":[27],"have":[28],"shown":[29],"promise":[30],"directly":[32],"computing":[33],"image-text":[34],"relations":[35],"without":[36,156],"relying":[37],"on":[38,162],"heavy":[39],"decoders.":[40,159],"However,":[41],"existing":[42],"methods":[43],"often":[44],"(i)":[45],"construct":[46,117],"cost":[47,121,145],"volumes":[48],"using":[49],"unfiltered":[50],"image":[51,112],"and":[52,59,65,78,113,116,135,170,184],"features,":[54,115],"overlooking":[55],"modality":[57],"imbalance":[58],"noise":[60],"inherent":[61],"in":[62,139],"VLM":[63,153],"embeddings,":[64,137],"(ii)":[66],"adopt":[67],"sequential":[68],"aggregation":[69,146],"mechanisms":[70],"that":[71,129,174],"limit":[72],"expressive":[74],"interaction":[75,132],"between":[76,111,133],"spatial":[77,134],"class":[79,136],"embeddings.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84,98,124],"present":[85],"CGSeg,":[86],"a":[87,100,118,126],"one-stage":[89,188],"framework":[90],"for":[91],"OVSS":[92,189],"with":[93,104],"two":[94],"key":[95],"modules.":[96],"First,":[97],"propose":[99],"gated":[101],"fusion":[102],"module":[103,128],"learnable":[105],"weights":[106],"adaptively":[108],"filter":[109],"information":[110],"more":[119,140],"reliable":[120],"volume.":[122],"Second,":[123],"design":[125],"cross-aggregation":[127],"enables":[130],"bidirectional":[131],"resulting":[138],"robust":[141],"correlations":[142],"during":[143],"stage.":[147],"Together,":[148],"proposed":[150,176],"components":[151],"enhance":[152],"performance":[155,180],"introducing":[157],"complex":[158],"Extensive":[160],"experiments":[161],"standard":[163],"benchmarks,":[165],"including":[166],"ADE20K,":[167],"Pascal":[168,171],"Context,":[169],"VOC,":[172],"demonstrate":[173],"our":[175],"CGSeg":[177],"achieves":[178],"state-of-the-art":[179],"while":[181],"maintaining":[182],"simplicity":[183],"efficiency":[185],"framework.":[190]},"counts_by_year":[],"updated_date":"2026-03-03T06:13:14.889584","created_date":"2026-02-24T00:00:00"}