{"id":"https://openalex.org/W4404988539","doi":"https://doi.org/10.1109/tip.2026.3688157","title":"SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation","display_name":"SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4404988539","doi":"https://doi.org/10.1109/tip.2026.3688157","pmid":"https://pubmed.ncbi.nlm.nih.gov/42090527"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3688157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3688157","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Transactions on Image Processing","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.17061","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084178891","display_name":"Guoan Xu","orcid":"https://orcid.org/0000-0002-0181-4140"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guoan Xu","raw_affiliation_strings":["Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0181-4140","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100712708","display_name":"Jiaming Chen","orcid":"https://orcid.org/0000-0001-9457-5259"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiaming Chen","raw_affiliation_strings":["Department of Computer Science, The University of Manchester, Manchester, U.K"],"raw_orcid":"https://orcid.org/0000-0003-2235-4101","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061199268","display_name":"Wenfeng Huang","orcid":"https://orcid.org/0000-0002-7948-9501"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenfeng Huang","raw_affiliation_strings":["Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9373-1720","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395314","display_name":"Wenjing Jia","orcid":"https://orcid.org/0000-0002-0940-3338"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenjing Jia","raw_affiliation_strings":["Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0940-3338","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038362365","display_name":"Guangwei Gao","orcid":"https://orcid.org/0000-0002-3950-1844"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwei Gao","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-3950-1844","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100766907","display_name":"Guo-Jun Qi","orcid":"https://orcid.org/0000-0003-3508-1851"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo-Jun Qi","raw_affiliation_strings":["Research Center for Industries of the Future and the School of Engineering, Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3508-1851","affiliations":[{"raw_affiliation_string":"Research Center for Industries of the Future and the School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00287099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"4847","last_page":"4860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.947700023651123,"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":0.947700023651123,"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":0.6798399686813354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6248789429664612},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42636406421661377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3774658143520355}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6798399686813354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6248789429664612},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42636406421661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3774658143520355}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tip.2026.3688157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3688157","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42090527","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42090527","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:arXiv.org:2411.17061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.17061","pdf_url":"https://arxiv.org/pdf/2411.17061","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":"","raw_type":"text"},{"id":"pmh:oai:arXiv.org:2411.17061","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2411.17061","pdf_url":"https://arxiv.org/pdf/2411.17061","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"},{"id":"doi:10.48550/arxiv.2411.17061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.17061","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:2411.17061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.17061","pdf_url":"https://arxiv.org/pdf/2411.17061","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G294318885","display_name":null,"funder_award_id":"ISN27-4","funder_id":"https://openalex.org/F4320330485","funder_display_name":"State Key Laboratory of Integrated Services Networks"}],"funders":[{"id":"https://openalex.org/F4320330485","display_name":"State Key Laboratory of Integrated Services Networks","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404988539.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,118],"Vision":[1],"Transformer":[2],"(ViT)":[3],"has":[4],"achieved":[5],"notable":[6],"success":[7],"in":[8,88],"computer":[9],"vision,":[10],"with":[11],"its":[12],"variants":[13],"widely":[14],"validated":[15],"across":[16,138,193],"various":[17,104,194],"downstream":[18],"tasks,":[19],"including":[20,203],"semantic":[21,49,64],"segmentation.":[22,50,65],"However,":[23],"as":[24,86],"general-purpose":[25],"visual":[26],"encoders,":[27],"ViT":[28],"backbones":[29],"often":[30],"do":[31],"not":[32],"fully":[33],"address":[34],"the":[35,70,122,159],"specific":[36],"requirements":[37],"of":[38,67,126,161],"task":[39],"decoders,":[40],"highlighting":[41],"opportunities":[42],"for":[43,47,63,114],"designing":[44],"decoders":[45],"optimized":[46],"efficient":[48],"This":[51],"paper":[52],"proposes":[53],"Strip":[54],"Cross-Attention":[55],"(SCASeg),":[56],"an":[57],"innovative":[58],"decoder":[59,81,107,189],"head":[60],"specifically":[61],"designed":[62],"Instead":[66],"relying":[68],"on":[69,200],"conventional":[71],"skip":[72],"connections,":[73],"we":[74,92],"utilize":[75],"lateral":[76],"connections":[77],"between":[78],"encoder":[79,84,105],"and":[80,106,116,134,148,163,175,208],"stages,":[82],"leveraging":[83],"features":[85],"Queries":[87],"cross-attention":[89],"modules.":[90],"Additionally,":[91],"introduce":[93],"a":[94,111],"Cross-Layer":[95],"Block":[96],"(CLB)":[97],"that":[98,171,186],"integrates":[99],"hierarchical":[100],"feature":[101,143],"maps":[102],"from":[103],"stages":[108],"to":[109,130,180],"form":[110],"unified":[112],"representation":[113],"Keys":[115],"Values.":[117],"CLB":[119],"also":[120],"incorporates":[121],"local":[123,135],"perceptual":[124],"strengths":[125],"convolution,":[127],"enabling":[128],"SCASeg":[129,157],"capture":[131],"both":[132],"global":[133],"context":[136],"dependencies":[137],"multiple":[139],"layers,":[140],"thus":[141],"enhancing":[142],"interaction":[144],"at":[145],"different":[146],"scales":[147],"improving":[149],"overall":[150],"efficiency.":[151],"To":[152],"further":[153],"optimize":[154],"computational":[155,214],"efficiency,":[156],"compresses":[158],"channels":[160],"queries":[162],"keys":[164],"into":[165],"one":[166],"dimension,":[167],"creating":[168],"strip-like":[169],"patterns":[170],"reduce":[172],"memory":[173],"usage":[174],"increase":[176],"inference":[177],"speed":[178],"compared":[179],"traditional":[181],"vanilla":[182],"cross-attention.":[183],"Experiments":[184],"show":[185],"SCASeg's":[187],"adaptable":[188],"delivers":[190],"competitive":[191],"performance":[192],"setups,":[195],"outperforming":[196],"leading":[197],"segmentation":[198],"architectures":[199],"benchmark":[201],"datasets,":[202],"ADE20K,":[204],"Cityscapes,":[205],"COCO-Stuff":[206],"164k,":[207],"Pascal":[209],"VOC2012,":[210],"even":[211],"under":[212],"diverse":[213],"constraints.":[215]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}