{"id":"https://openalex.org/W4399074042","doi":"https://doi.org/10.1109/tmm.2024.3396281","title":"Pyramid Fusion Transformer for Semantic Segmentation","display_name":"Pyramid Fusion Transformer for Semantic Segmentation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399074042","doi":"https://doi.org/10.1109/tmm.2024.3396281"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3396281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3396281","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5010409434","display_name":"Zipeng Qin","orcid":"https://orcid.org/0000-0001-7907-3832"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zipeng Qin","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7907-3832","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361599","display_name":"Jianbo Liu","orcid":"https://orcid.org/0000-0003-4392-1056"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbo Liu","raw_affiliation_strings":["SenseTime Research, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-4392-1056","affiliations":[{"raw_affiliation_string":"SenseTime Research, Hong Kong","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115547313","display_name":"Xiaolin Zhang","orcid":"https://orcid.org/0000-0001-7303-5712"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Zhang","raw_affiliation_strings":["SenseTime Research, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7303-5712","affiliations":[{"raw_affiliation_string":"SenseTime Research, Hong Kong","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091706919","display_name":"Maoqing Tian","orcid":"https://orcid.org/0000-0003-2438-4072"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maoqing Tian","raw_affiliation_strings":["SenseTime Research, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-2438-4072","affiliations":[{"raw_affiliation_string":"SenseTime Research, Hong Kong","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041431476","display_name":"Aojun Zhou","orcid":"https://orcid.org/0000-0002-4742-8624"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Aojun Zhou","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-4742-8624","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101696728","display_name":"Shuai Yi","orcid":"https://orcid.org/0000-0002-1253-6633"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Yi","raw_affiliation_strings":["SenseTime Research, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-1253-6633","affiliations":[{"raw_affiliation_string":"SenseTime Research, Hong Kong","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100732450","display_name":"Hongsheng Li","orcid":"https://orcid.org/0000-0002-2664-7975"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongsheng Li","raw_affiliation_strings":["Multimedia Laboratory, The Chinese University of Hong Kong, Hong Kong","Multimedia Laboratory, The Chinese University of Hong Kong, Centre for Perceptual and Interative Intelligence (CPII), and Shanghai AI Laboratory"],"raw_orcid":"https://orcid.org/0000-0002-2664-7975","affiliations":[{"raw_affiliation_string":"Multimedia Laboratory, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Multimedia Laboratory, The Chinese University of Hong Kong, Centre for Perceptual and Interative Intelligence (CPII), and Shanghai AI Laboratory","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4455,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95061907,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"9630","last_page":"9643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.5637000203132629,"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/T10320","display_name":"Neural Networks and Applications","score":0.5637000203132629,"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/computer-science","display_name":"Computer science","score":0.8057162165641785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6242033839225769},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5883090496063232},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5445757508277893},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.46917349100112915},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.46334773302078247},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4620027244091034},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.42241179943084717},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39078524708747864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057162165641785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6242033839225769},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5883090496063232},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5445757508277893},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.46917349100112915},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.46334773302078247},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4620027244091034},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.42241179943084717},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39078524708747864},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3396281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3396281","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2117539524","https://openalex.org/W2125215748","https://openalex.org/W2194775991","https://openalex.org/W2507296351","https://openalex.org/W2560023338","https://openalex.org/W2561196672","https://openalex.org/W2565639579","https://openalex.org/W2601564443","https://openalex.org/W2630837129","https://openalex.org/W2742400085","https://openalex.org/W2752782242","https://openalex.org/W2787091153","https://openalex.org/W2883780447","https://openalex.org/W2910628332","https://openalex.org/W2962914239","https://openalex.org/W2963341956","https://openalex.org/W2963351448","https://openalex.org/W2963855133","https://openalex.org/W2982770724","https://openalex.org/W3028392891","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3096653763","https://openalex.org/W3097762837","https://openalex.org/W3106728613","https://openalex.org/W3107497254","https://openalex.org/W3107653507","https://openalex.org/W3110440461","https://openalex.org/W3121626821","https://openalex.org/W3138516171","https://openalex.org/W3157386596","https://openalex.org/W3159637683","https://openalex.org/W3159746229","https://openalex.org/W3168649818","https://openalex.org/W3170841864","https://openalex.org/W3170885821","https://openalex.org/W3174598330","https://openalex.org/W3196107618","https://openalex.org/W3197715576","https://openalex.org/W3199130398","https://openalex.org/W3203974803","https://openalex.org/W3204874447","https://openalex.org/W3214466318","https://openalex.org/W3214707056","https://openalex.org/W4210786150","https://openalex.org/W4214627427","https://openalex.org/W4225557002","https://openalex.org/W4286982960","https://openalex.org/W4293680532","https://openalex.org/W4312235312","https://openalex.org/W4312815172","https://openalex.org/W4313007769","https://openalex.org/W4385245566","https://openalex.org/W4388286388","https://openalex.org/W4390189979","https://openalex.org/W4390872217","https://openalex.org/W6735160876","https://openalex.org/W6739696289","https://openalex.org/W6757817989","https://openalex.org/W6778231270","https://openalex.org/W6784094891","https://openalex.org/W6788135285","https://openalex.org/W6796761347","https://openalex.org/W6797399245","https://openalex.org/W6798837711","https://openalex.org/W6804295845"],"related_works":["https://openalex.org/W1986655823","https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W3144569342","https://openalex.org/W3011384228","https://openalex.org/W2945274617","https://openalex.org/W3199300986","https://openalex.org/W4313052709","https://openalex.org/W4298131179","https://openalex.org/W2375430703"],"abstract_inverted_index":{"The":[0,101],"recently":[1],"proposed":[2,102,209],"MaskFormer":[3],"[1]":[4],"gives":[5],"a":[6,24,62,87,158,177],"refreshed":[7],"perspective":[8],"on":[9,59,134,143,192,197],"the":[10,18,46,55,82,108,116,193,205],"task":[11],"of":[12,61,155,207],"semantic":[13,79,96,138,201],"segmentation:":[14],"it":[15,30],"shifts":[16],"from":[17,115],"popular":[19],"pixel-level":[20],"classification":[21,26,57],"paradigm":[22],"to":[23,37,69,126],"mask-level":[25],"method.":[27,210],"In":[28,49,141],"essence,":[29],"generates":[31],"paired":[32],"probabilities":[33,72],"and":[34,40,111,121,166,172,185],"masks":[35],"corresponding":[36],"category":[38],"segments":[39],"combines":[41],"them":[42],"during":[43],"inference":[44],"for":[45,77,93],"segmentation":[47,97,139,202],"maps.":[48],"our":[50,148,208],"study,":[51],"we":[52,85,180],"find":[53],"that":[54,154],"per-mask":[56,94],"decoder":[58,104],"top":[60],"single-scale":[63,165,182],"feature":[64,83,114,117],"is":[65],"not":[66],"effective":[67],"enough":[68],"extract":[70],"reliable":[71],"or":[73],"masks.":[74],"To":[75],"mine":[76],"rich":[78],"information":[80],"across":[81],"pyramid,":[84],"propose":[86],"transformer-based":[88],"Pyramid":[89],"Fusion":[90],"Transformer":[91],"(PFT)":[92],"approach":[95],"with":[98,150,157],"multi-scale":[99,167,186],"features.":[100],"transformer":[103],"performs":[105],"cross-attention":[106],"between":[107],"learnable":[109],"queries":[110],"each":[112],"spatial":[113],"pyramid":[118],"in":[119,163],"parallel":[120],"uses":[122],"cross-scale":[123],"inter-query":[124],"attention":[125],"exchange":[127],"complimentary":[128],"information.":[129],"We":[130],"achieve":[131,181],"competitive":[132],"performance":[133,191],"three":[135,198],"widely":[136,199],"used":[137,200],"datasets.":[140],"particular,":[142],"ADE20":[144],"K":[145],"validation":[146],"set,":[147],"result":[149],"Swin-B":[151],"backbone":[152,162],"surpasses":[153],"MaskFormer's":[156],"much":[159],"larger":[160],"Swin-L":[161,178],"both":[164],"inference,":[168],"achieving":[169],"54.1":[170],"mIoU":[171,174,184],"55.7":[173],"respectively.":[175],"Using":[176],"backbone,":[179],"56.1":[183],"57.4":[187],"mIoU,":[188],"obtaining":[189],"state-of-the-art":[190],"dataset.":[194],"Extensive":[195],"experiments":[196],"datasets":[203],"verify":[204],"effectiveness":[206]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}