{"id":"https://openalex.org/W4412063814","doi":"https://doi.org/10.32604/cmc.2025.064537","title":"CGMISeg: Context-Guided Multi-Scale Interactive for Efficient Semantic Segmentation","display_name":"CGMISeg: Context-Guided Multi-Scale Interactive for Efficient Semantic Segmentation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412063814","doi":"https://doi.org/10.32604/cmc.2025.064537"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.064537","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064537","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.32604/cmc.2025.064537","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064443447","display_name":"Ze Wang","orcid":"https://orcid.org/0000-0003-3718-2605"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ze Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662807","display_name":"Jing Qin","orcid":"https://orcid.org/0000-0002-7059-0929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Qin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088456452","display_name":"Chuhua Huang","orcid":"https://orcid.org/0000-0003-3288-3701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuhua Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100325619","display_name":"Yongjun Zhang","orcid":"https://orcid.org/0000-0003-4276-9072"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongjun Zhang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064443447"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.319,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8261002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"84","issue":"3","first_page":"5811","last_page":"5829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9864000082015991,"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":0.9864000082015991,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9726999998092651,"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":0.9598000049591064,"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/computer-science","display_name":"Computer science","score":0.6673028469085693},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.611996054649353},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5876759886741638},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49986815452575684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4262898862361908},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3964202404022217},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.12291967868804932},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09897270798683167},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.09028387069702148}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6673028469085693},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.611996054649353},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5876759886741638},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49986815452575684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4262898862361908},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3964202404022217},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.12291967868804932},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09897270798683167},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.09028387069702148},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.32604/cmc.2025.064537","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064537","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.32604/cmc.2025.064537","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064537","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2395611524","https://openalex.org/W2886934227","https://openalex.org/W2964309882","https://openalex.org/W3014641072","https://openalex.org/W3196904463","https://openalex.org/W4385391093","https://openalex.org/W4391097085"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4385583601","https://openalex.org/W4395685956","https://openalex.org/W3159516372","https://openalex.org/W4398146871","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,16,34,51,173],"has":[2],"made":[3],"significant":[4,170],"breakthroughs":[5],"in":[6,103,172,225],"various":[7],"application":[8],"fields,":[9],"but":[10],"achieving":[11],"both":[12,104,248],"accurate":[13],"and":[14,64,80,106,137,155,162,177,188,199,219,223,234,244,250,261],"efficient":[15,32],"with":[17,127,209],"limited":[18],"computational":[19,47,175,232,249],"resources":[20],"remains":[21],"a":[22,38],"major":[23],"challenge.":[24],"To":[25],"this":[26],"end,":[27],"we":[28],"propose":[29],"CGMISeg,":[30],"an":[31,239],"semantic":[33],"architecture":[35],"based":[36],"on":[37,113,152,205],"context-guided":[39],"multi-scale":[40,135],"interaction":[41,136],"strategy,":[42],"aiming":[43],"to":[44,73,121,142],"significantly":[45,246],"reduce":[46],"overhead":[48],"while":[49,228,253],"maintaining":[50,254],"accuracy.":[52],"CGMISeg":[53,151,168,191,237],"consists":[54],"of":[55],"three":[56,157],"core":[57],"components:":[58],"context-aware":[59],"attention":[60,68,82],"modulation,":[61],"feature":[62,85],"reconstruction,":[63],"cross-information":[65,117],"fusion.":[66],"Context-aware":[67],"modulation":[69],"is":[70],"carefully":[71],"designed":[72],"capture":[74],"key":[75,95],"contextual":[76,89,101],"information":[77,90,102],"through":[78],"channel":[79],"spatial":[81],"mechanisms.":[83],"The":[84,116],"reconstruction":[86],"module":[87,119],"reconstructs":[88],"from":[91],"different":[92,146],"scales,":[93],"modeling":[94],"rectangular":[96],"areas":[97],"by":[98,221],"capturing":[99],"critical":[100],"horizontal":[105],"vertical":[107],"directions,":[108],"thereby":[109],"enhancing":[110,138,247],"the":[111,123,128,139,163,206],"focus":[112],"foreground":[114],"features.":[115],"fusion":[118],"aims":[120],"fuse":[122],"reconstructed":[124],"high-level":[125],"features":[126,131],"original":[129],"low-level":[130],"during":[132],"upsampling,":[133],"promoting":[134],"model\u2019s":[140],"ability":[141],"handle":[143],"objects":[144],"at":[145],"scales.":[147],"We":[148],"extensively":[149],"evaluated":[150],"ADE20K,":[153],"Cityscapes,":[154],"COCO-Stuff,":[156],"widely":[158],"used":[159],"datasets":[160],"benchmarks,":[161],"experimental":[164],"results":[165],"show":[166],"that":[167],"exhibits":[169],"advantages":[171],"performance,":[174],"efficiency,":[176,245],"inference":[178,251],"speed,":[179],"clearly":[180],"outperforming":[181,217],"several":[182],"mainstream":[183],"methods,":[184],"including":[185],"SegFormer,":[186],"Feedformer,":[187],"SegNext.":[189],"Specifically,":[190],"achieves":[192],"42.9%":[193],"mIoU":[194],"(Mean":[195],"Intersection":[196],"over":[197],"Union)":[198],"15.7":[200],"FPS":[201],"(Frames":[202],"Per":[203,215],"Second)":[204],"ADE20K":[207],"dataset":[208],"3.8":[210],"GFLOPs":[211],"(Giga":[212],"Floating-point":[213],"Operations":[214],"Second),":[216],"Feedformer":[218],"SegNeXt":[220],"3.7%":[222],"1.8%":[224],"mIoU,":[226],"respectively,":[227],"also":[229],"offering":[230],"reduced":[231],"complexity":[233],"faster":[235],"inference.":[236],"strikes":[238],"excellent":[240],"balance":[241],"between":[242],"accuracy":[243],"performance":[252],"high":[255],"precision,":[256],"showcasing":[257],"exceptional":[258],"practical":[259],"value":[260],"strong":[262],"potential":[263],"for":[264],"widespread":[265],"applications.":[266]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}