{"id":"https://openalex.org/W7154642527","doi":"https://doi.org/10.1109/lsp.2026.3684447","title":"CaSS: Category-Aware Semantic Segmentation With Vision\u2013Language Priors","display_name":"CaSS: Category-Aware Semantic Segmentation With Vision\u2013Language Priors","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7154642527","doi":"https://doi.org/10.1109/lsp.2026.3684447"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2026.3684447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3684447","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"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 Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033579560","display_name":"Quan Tang","orcid":"https://orcid.org/0000-0003-4011-6166"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Tang","raw_affiliation_strings":["Department of New Network, Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4011-6166","affiliations":[{"raw_affiliation_string":"Department of New Network, Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030715932","display_name":"D H Zhang","orcid":"https://orcid.org/0009-0001-2941-0084"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengke Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-2941-0084","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032307060","display_name":"Xuhao Tang","orcid":"https://orcid.org/0000-0001-7548-9988"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuhao Tang","raw_affiliation_strings":["Department of New Network, Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7548-9988","affiliations":[{"raw_affiliation_string":"Department of New Network, Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073236866","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0001-8861-571X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Department of New Network, Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8861-571X","affiliations":[{"raw_affiliation_string":"Department of New Network, Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133764360","display_name":"Cuifeng Du","orcid":"https://orcid.org/0000-0002-9055-6381"},"institutions":[{"id":"https://openalex.org/I4210164767","display_name":"GCI Science & Technology (China)","ror":"https://ror.org/05tj2eg80","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210164767"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cuifeng Du","raw_affiliation_strings":["CETC Potevio Science and Technology Company Ltd., Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9055-6381","affiliations":[{"raw_affiliation_string":"CETC Potevio Science and Technology Company Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I4210164767"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010421115","display_name":"Jun Jiang","orcid":"https://orcid.org/0000-0002-8406-994X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Jiang","raw_affiliation_strings":["Department of New Network, Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8406-994X","affiliations":[{"raw_affiliation_string":"Department of New Network, Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.565604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1651","last_page":"1655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.40720000863075256,"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":0.40720000863075256,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.37400001287460327,"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":0.07020000368356705,"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/prior-probability","display_name":"Prior probability","score":0.5644999742507935},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5153999924659729},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5037000179290771},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.44429999589920044},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.33149999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7231000065803528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6703000068664551},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5644999742507935},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5153999924659729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5037000179290771},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.44429999589920044},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.33149999380111694},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2800000011920929}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2026.3684447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3684447","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5135065913200378}],"awards":[{"id":"https://openalex.org/G7664549778","display_name":null,"funder_award_id":"2025M771700","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2031489346","https://openalex.org/W2112796928","https://openalex.org/W2125215748","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W3145698611","https://openalex.org/W3170841864","https://openalex.org/W4214893857","https://openalex.org/W4224238952","https://openalex.org/W4312744505","https://openalex.org/W4312815172","https://openalex.org/W4324368760","https://openalex.org/W4385245566","https://openalex.org/W4387975548","https://openalex.org/W4402275786","https://openalex.org/W4402727633","https://openalex.org/W4403068531","https://openalex.org/W4407097610","https://openalex.org/W4407315228","https://openalex.org/W4407724320","https://openalex.org/W4407740919","https://openalex.org/W4410489121","https://openalex.org/W7108225818","https://openalex.org/W7160128869"],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"image":[1],"segmentation":[2,38,146,153],"typically":[3],"relies":[4],"on":[5,143],"static":[6],"pixel-":[7,94],"wise":[8,95],"classifiers":[9],"that":[10,40,88,149],"operate":[11],"over":[12,155],"a":[13,26,35,51,72,83,123],"fixed":[14],"category":[15,74],"space,":[16],"making":[17],"them":[18],"insensitive":[19],"to":[20,45,57,81],"the":[21,59,100,129],"actual":[22],"semantic":[23,37,43,62,131,145],"composition":[24],"of":[25,61,133],"real-world":[27],"image.":[28],"In":[29],"this":[30],"work,":[31],"we":[32],"propose":[33],"CaSS,":[34],"category-aware":[36,103],"framework":[39],"introduces":[41],"image-level":[42],"priors":[44],"dynamically":[46],"adapt":[47],"pixel-level":[48,139],"classification.":[49],"Specifically,":[50],"pre-trained":[52],"vision\u2013language":[53,134],"model":[54,125],"is":[55,69,78],"employed":[56],"infer":[58],"set":[60],"categories":[63],"present":[64],"in":[65],"an":[66],"image,":[67],"which":[68],"encoded":[70],"as":[71],"structured":[73],"prior.":[75],"This":[76],"prior":[77],"then":[79],"used":[80],"drive":[82],"lightweight":[84],"dynamic":[85],"parsing":[86],"network":[87],"generates":[89],"image-conditioned":[90],"classifier":[91,101],"parameters":[92],"for":[93],"segmentation.":[96],"By":[97],"explicitly":[98],"constraining":[99],"with":[102,158],"priors,":[104],"CaSS":[105,150],"reduces":[106],"interference":[107],"from":[108],"absent":[109],"classes":[110],"and":[111,116],"enhances":[112],"both":[113],"intra-class":[114],"consistency":[115],"inter-class":[117],"discriminability.":[118],"The":[119],"proposed":[120],"approach":[121],"follows":[122],"large\u2013small":[124],"collaboration":[126],"paradigm,":[127],"leveraging":[128],"strong":[130],"understanding":[132],"models":[135],"while":[136],"preserving":[137],"efficient":[138],"inference.":[140],"Extensive":[141],"experiments":[142],"standard":[144],"benchmarks":[147],"demonstrate":[148],"consistently":[151],"improves":[152],"accuracy":[154],"state-of-the-art":[156],"methods":[157],"minimal":[159],"parameter":[160],"overhead.":[161]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-17T00:00:00"}