{"id":"https://openalex.org/W4293680532","doi":"https://doi.org/10.1109/tpami.2022.3202765","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","display_name":"P2T: Pyramid Pooling Transformer for Scene Understanding","publication_year":2022,"publication_date":"2022-08-30","ids":{"openalex":"https://openalex.org/W4293680532","doi":"https://doi.org/10.1109/tpami.2022.3202765","pmid":"https://pubmed.ncbi.nlm.nih.gov/36040936"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3202765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3202765","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5001598042","display_name":"Yu-Huan Wu","orcid":"https://orcid.org/0000-0001-8666-3435"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Huan Wu","raw_affiliation_strings":["TMCC, College of Computer Science, Nankai University, Tianjin, China","Alibaba DAMO Academy, Hangzhou, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8666-3435","affiliations":[{"raw_affiliation_string":"TMCC, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056961910","display_name":"Yun Liu","orcid":"https://orcid.org/0000-0001-6143-0264"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yun Liu","raw_affiliation_strings":["Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6143-0264","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028120929","display_name":"Xin Zhan","orcid":"https://orcid.org/0000-0003-0552-093X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhan","raw_affiliation_strings":["Alibaba DAMO Academy, Hangzhou, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Hangzhou, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037131575","display_name":"Ming\u2010Ming Cheng","orcid":"https://orcid.org/0000-0001-5550-8758"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Ming Cheng","raw_affiliation_strings":["TMCC, College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5550-8758","affiliations":[{"raw_affiliation_string":"TMCC, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":26.1341,"has_fulltext":false,"cited_by_count":293,"citation_normalized_percentile":{"value":0.9979856,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"45","issue":"11","first_page":"12760","last_page":"12771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9997000098228455,"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/pooling","display_name":"Pooling","score":0.909687876701355},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.675805926322937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6666288375854492},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6415045857429504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5805627107620239},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5563510656356812},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41292011737823486},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.4105132520198822},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34108659625053406},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13583612442016602},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09483286738395691}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.909687876701355},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.675805926322937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6666288375854492},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6415045857429504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5805627107620239},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5563510656356812},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41292011737823486},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.4105132520198822},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34108659625053406},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13583612442016602},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09483286738395691},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2022.3202765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3202765","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:36040936","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36040936","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3432882601","display_name":null,"funder_award_id":"61922046","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":92,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1932481952","https://openalex.org/W2031489346","https://openalex.org/W2097117768","https://openalex.org/W2104978738","https://openalex.org/W2109255472","https://openalex.org/W2117539524","https://openalex.org/W2162915993","https://openalex.org/W2194775991","https://openalex.org/W2257408573","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2549139847","https://openalex.org/W2560023338","https://openalex.org/W2565516711","https://openalex.org/W2737258237","https://openalex.org/W2780708736","https://openalex.org/W2806070179","https://openalex.org/W2883780447","https://openalex.org/W2888036988","https://openalex.org/W2894878591","https://openalex.org/W2899663614","https://openalex.org/W2910121883","https://openalex.org/W2910628332","https://openalex.org/W2928165649","https://openalex.org/W2945472816","https://openalex.org/W2963017889","https://openalex.org/W2963032190","https://openalex.org/W2963062226","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W2963306157","https://openalex.org/W2963351448","https://openalex.org/W2963420686","https://openalex.org/W2963619659","https://openalex.org/W2963918968","https://openalex.org/W2982083293","https://openalex.org/W3009131247","https://openalex.org/W3082631269","https://openalex.org/W3083291461","https://openalex.org/W3096609285","https://openalex.org/W3100321043","https://openalex.org/W3114848016","https://openalex.org/W3119586106","https://openalex.org/W3121523901","https://openalex.org/W3122239467","https://openalex.org/W3131500599","https://openalex.org/W3136416617","https://openalex.org/W3137142667","https://openalex.org/W3138516171","https://openalex.org/W3139049060","https://openalex.org/W3139633126","https://openalex.org/W3143320354","https://openalex.org/W3153842237","https://openalex.org/W3156811085","https://openalex.org/W3159833358","https://openalex.org/W3165745140","https://openalex.org/W3168649818","https://openalex.org/W3169745417","https://openalex.org/W3172099915","https://openalex.org/W3172345956","https://openalex.org/W3175515048","https://openalex.org/W3207918547","https://openalex.org/W4205688290","https://openalex.org/W4214493665","https://openalex.org/W4214588794","https://openalex.org/W4214614183","https://openalex.org/W4214636423","https://openalex.org/W4226354398","https://openalex.org/W4288325606","https://openalex.org/W4297775537","https://openalex.org/W4300273322","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6755977528","https://openalex.org/W6757817989","https://openalex.org/W6762718338","https://openalex.org/W6764322716","https://openalex.org/W6780226713","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6791776128","https://openalex.org/W6792695861","https://openalex.org/W6793632291","https://openalex.org/W6794345597","https://openalex.org/W6794906783","https://openalex.org/W6794978867","https://openalex.org/W6796004790","https://openalex.org/W6796750486"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2022849497","https://openalex.org/W2407190427","https://openalex.org/W3081299480","https://openalex.org/W2919210741","https://openalex.org/W2907584218","https://openalex.org/W3002446410","https://openalex.org/W4390224712","https://openalex.org/W4322096758"],"abstract_inverted_index":{"Recently,":[0],"the":[1,10,18,23,28,57,70,134,139,172],"vision":[2,14,24,67,98,135,156,181],"transformer":[3,25,157],"has":[4,90,111],"achieved":[5],"great":[6],"success":[7],"by":[8,74],"pushing":[9],"state-of-the-art":[11],"of":[12,17,32],"various":[13,97,180],"tasks.":[15],"One":[16],"most":[19],"challenging":[20],"problems":[21],"in":[22,96,105,115,133,179],"is":[26,48],"that":[27,87],"large":[29],"sequence":[30,58,140],"length":[31,141],"image":[33,185],"tokens":[34],"leads":[35],"to":[36,45,49,55,64,93,101,125,129,195],"high":[37],"computational":[38],"cost":[39],"(quadratic":[40],"complexity).":[41],"A":[42],"popular":[43],"solution":[44],"this":[46,83,121],"problem":[47],"use":[50],"a":[51,75,154],"single":[52,76],"pooling":[53,77,89,110,128],"operation":[54,78],"reduce":[56],"length.":[59],"This":[60],"paper":[61],"considers":[62],"how":[63],"improve":[65],"existing":[66],"transformers,":[68],"where":[69],"pooled":[71],"feature":[72],"extracted":[73],"seems":[79],"less":[80],"powerful.":[81],"To":[82,119],"end,":[84],"we":[85,123,152],"note":[86],"pyramid":[88,109,127],"been":[91,113],"demonstrated":[92],"be":[94,204],"effective":[95],"tasks":[99,182],"owing":[100],"its":[102],"powerful":[103,144],"ability":[104],"context":[106],"abstraction.":[107],"However,":[108],"not":[112],"explored":[114],"backbone":[116,173],"network":[117],"design.":[118],"bridge":[120],"gap,":[122],"propose":[124],"adapt":[126],"Multi-Head":[130],"Self-Attention":[131],"(MHSA)":[132],"transformer,":[136],"simultaneously":[137],"reducing":[138],"and":[142,191,198],"capturing":[143],"contextual":[145],"features.":[146],"Plugged":[147],"with":[148],"our":[149],"pooling-based":[150],"MHSA,":[151],"build":[153],"universal":[155],"backbone,":[158],"dubbed":[159],"Pyramid":[160],"Pooling":[161],"Transformer":[162],"(P2T).":[163],"Extensive":[164],"experiments":[165],"demonstrate":[166],"that,":[167],"when":[168],"applied":[169],"P2T":[170],"as":[171,184],"network,":[174],"it":[175],"shows":[176],"substantial":[177],"superiority":[178],"such":[183],"classification,":[186],"semantic":[187],"segmentation,":[188,193],"object":[189],"detection,":[190],"instance":[192],"compared":[194],"previous":[196],"CNN-":[197],"transformer-based":[199],"networks.":[200],"The":[201],"code":[202],"will":[203],"released":[205],"at":[206],"https://github.com/yuhuan-wu/P2T.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":22},{"year":2025,"cited_by_count":83},{"year":2024,"cited_by_count":91},{"year":2023,"cited_by_count":79},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}