{"id":"https://openalex.org/W7123353731","doi":"https://doi.org/10.1109/tcsvt.2026.3651347","title":"Balancing Performance and Efficiency: Toward Superior Image Segmentation With Adaptive Sparse Attention","display_name":"Balancing Performance and Efficiency: Toward Superior Image Segmentation With Adaptive Sparse Attention","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123353731","doi":"https://doi.org/10.1109/tcsvt.2026.3651347"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3651347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3651347","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5122893337","display_name":"Xiaoqing Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqing Zhao","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-6361-9460","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007788482","display_name":"Chaojun Zhang","orcid":"https://orcid.org/0000-0002-8195-9322"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaojun Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Hainan University, Haikou, China"],"raw_orcid":"https://orcid.org/0000-0002-8195-9322","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122895033","display_name":"Yuan Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Gao","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4096-9134","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Yang","orcid":"https://orcid.org/0009-0000-4682-4839"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-4682-4839","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122901674","display_name":"Laurence T. Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Laurence T. Yang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7986-4244","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113978259","display_name":"Jieming Yang","orcid":"https://orcid.org/0000-0001-9584-2160"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieming Yang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9584-2160","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.05283783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"7337","last_page":"7351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9193999767303467,"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":0.9193999767303467,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.013799999840557575,"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":0.012400000356137753,"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":0.6162999868392944},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5727999806404114},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5139999985694885},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5054000020027161},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44909998774528503},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.40529999136924744},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.39820000529289246},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.3837999999523163},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.375900000333786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968000173568726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7075999975204468},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6162999868392944},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5727999806404114},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5139999985694885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5054000020027161},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4984000027179718},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.40529999136924744},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.375900000333786},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3237000107765198},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3158000111579895},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3068000078201294},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.288100004196167},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3651347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3651347","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5447995662689209}],"awards":[{"id":"https://openalex.org/G214697123","display_name":null,"funder_award_id":"62302130","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"most":[1],"image":[2],"segmentation":[3,29,43,145],"methods":[4,26],"exhibit":[5],"an":[6],"extreme":[7],"trade-off":[8],"between":[9,66],"performance":[10,18,67,139],"and":[11,50,68,79,82,143],"efficiency,":[12,23],"resulting":[13],"in":[14,140],"approaches":[15],"with":[16,90,94,120,156,177],"high":[17],"typically":[19],"having":[20],"low":[21],"computational":[22],"while":[24,127,164],"efficient":[25,42],"compromise":[27],"on":[28,46,160],"accuracy.":[30],"To":[31],"address":[32],"this":[33,36,133],"dual":[34],"challenge,":[35],"study":[37],"introduces":[38],"a":[39,58,74,95],"simple":[40],"yet":[41],"framework":[44],"based":[45],"Multi-scale":[47],"Prototype":[48],"matching":[49],"visual":[51,92],"Sparse":[52],"Attention":[53],"mechanisms":[54],"(MPSA),":[55],"which":[56],"is":[57,184],"transformer-based":[59],"architecture":[60],"designed":[61],"to":[62,85,166,173],"optimize":[63],"the":[64,102,161],"balance":[65],"efficiency.":[69],"The":[70],"proposed":[71],"MPSA":[72,136,151],"integrates":[73],"novel":[75],"lightweight":[76],"cross-attention":[77],"mechanism":[78],"prototype":[80],"selection":[81],"filtering":[83],"strategy":[84],"accurately":[86],"correlate":[87],"category":[88],"queries":[89],"corresponding":[91],"objects":[93],"multi-scale":[96],"Feature":[97],"Pyramid":[98],"Network":[99],"(FPN).":[100],"Within":[101],"pixel":[103],"decoder,":[104],"our":[105],"Axial":[106],"Convolution":[107],"Enhanced":[108],"(ACE)":[109],"module":[110],"mitigates":[111],"lost":[112],"global":[113,125],"context":[114],"by":[115],"combining":[116],"depth-wise":[117],"separable":[118],"convolutions":[119],"deformable":[121],"convolutions,":[122],"thereby":[123],"recovering":[124],"semantics":[126],"preserving":[128],"fine-grained":[129],"spatial":[130],"details.":[131],"Through":[132],"innovative":[134],"design,":[135],"demonstrates":[137],"outstanding":[138],"both":[141],"semantic":[142],"panoptic":[144],"tasks":[146],"across":[147],"multiple":[148],"datasets.":[149],"Remarkably,":[150],"achieves":[152],"surprising":[153],"83.9%":[154],"mIoU":[155],"only":[157],"114M":[158],"parameters":[159],"Cityscapes":[162],"dataset":[163],"compared":[165],"some":[167],"state-of-the-art":[168],"architectures,":[169],"highlighting":[170],"its":[171],"ability":[172],"deliver":[174],"exceptional":[175],"results":[176],"significantly":[178],"reduced":[179],"resource":[180],"consumption.":[181],"Our":[182],"code":[183],"released":[185],"at":[186],"https://github.com/zxqing01/MPSA.":[187]},"counts_by_year":[],"updated_date":"2026-05-08T13:12:06.581006","created_date":"2026-01-14T00:00:00"}