{"id":"https://openalex.org/W3214466318","doi":"https://doi.org/10.1109/tmm.2021.3120873","title":"EAPT: Efficient Attention Pyramid Transformer for Image Processing","display_name":"EAPT: Efficient Attention Pyramid Transformer for Image Processing","publication_year":2021,"publication_date":"2021-10-20","ids":{"openalex":"https://openalex.org/W3214466318","doi":"https://doi.org/10.1109/tmm.2021.3120873","mag":"3214466318"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3120873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3120873","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/A5100450522","display_name":"Xiao Lin","orcid":"https://orcid.org/0000-0002-8805-7129"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Lin","raw_affiliation_strings":["Department of Computer Science, Shanghai Normal University, Shanghai, China","Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8805-7129","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077549875","display_name":"Shuzhou Sun","orcid":"https://orcid.org/0000-0001-8453-3346"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuzhou Sun","raw_affiliation_strings":["Department of Computer Science, Shanghai Normal University, Shanghai, China","Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101640379","display_name":"Wei Huang","orcid":"https://orcid.org/0000-0001-9311-7299"},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Huang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I148128674"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bin Sheng","orcid":"https://orcid.org/0000-0001-8510-2556"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Sheng","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8510-2556","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435494","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-1503-0240"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-1503-0240","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068891693","display_name":"Dagan Feng","orcid":"https://orcid.org/0000-0002-3381-214X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Dagan Feng","raw_affiliation_strings":["Biomedical and Multimedia Information Technology Research Group, School of Information Technologies, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3381-214X","affiliations":[{"raw_affiliation_string":"Biomedical and Multimedia Information Technology Research Group, School of Information Technologies, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":22.2376,"has_fulltext":false,"cited_by_count":578,"citation_normalized_percentile":{"value":0.99809666,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"50","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/computer-science","display_name":"Computer science","score":0.8501696586608887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6536238789558411},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5857272148132324},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.584398090839386},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5753130912780762},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5428053140640259},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.48108240962028503},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41303062438964844},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38610613346099854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8501696586608887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6536238789558411},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5857272148132324},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.584398090839386},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5753130912780762},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5428053140640259},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.48108240962028503},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41303062438964844},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38610613346099854},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3120873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3120873","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":[{"id":"https://openalex.org/G2153763981","display_name":null,"funder_award_id":"17411952600","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G4233441832","display_name":null,"funder_award_id":"P0035358","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G7196794454","display_name":null,"funder_award_id":"18410750700","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G745752996","display_name":null,"funder_award_id":"P0030929","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G7808128244","display_name":"\u51e0\u4f55\u7ed3\u6784\u5f15\u5bfc\u7684\u5168\u666f\u89c6\u9891\u6c89\u6d78\u5f0f\u663e\u793a\u6280\u672f\u7814\u7a76","funder_award_id":"61872241","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7967749724","display_name":null,"funder_award_id":"62077037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8006193334","display_name":null,"funder_award_id":"P0030419","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2507296351","https://openalex.org/W2588926130","https://openalex.org/W2787091153","https://openalex.org/W2788730650","https://openalex.org/W2806070179","https://openalex.org/W2884822772","https://openalex.org/W2891969803","https://openalex.org/W2912423076","https://openalex.org/W2916798096","https://openalex.org/W2955058313","https://openalex.org/W2956367483","https://openalex.org/W2963749936","https://openalex.org/W2963849369","https://openalex.org/W2963925437","https://openalex.org/W2964035467","https://openalex.org/W2964241181","https://openalex.org/W2982220924","https://openalex.org/W2982560934","https://openalex.org/W2991062542","https://openalex.org/W2998776895","https://openalex.org/W3012835873","https://openalex.org/W3016719260","https://openalex.org/W3018757597","https://openalex.org/W3026441479","https://openalex.org/W3034429256","https://openalex.org/W3034512672","https://openalex.org/W3034971973","https://openalex.org/W3035087309","https://openalex.org/W3035396860","https://openalex.org/W3096609285","https://openalex.org/W3097195714","https://openalex.org/W3100219394","https://openalex.org/W3107634219","https://openalex.org/W3127867299","https://openalex.org/W3138516171","https://openalex.org/W3159637683","https://openalex.org/W3171125843","https://openalex.org/W3172752666","https://openalex.org/W3175630421","https://openalex.org/W3176659256","https://openalex.org/W3187216907","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6762718338","https://openalex.org/W6777046832","https://openalex.org/W6780959388","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6784923365","https://openalex.org/W6788135285"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147","https://openalex.org/W2039176012"],"abstract_inverted_index":{"Recent":[0],"transformer-based":[1],"models,":[2],"especially":[3],"patch-based":[4,47],"methods,":[5],"have":[6],"shown":[7],"huge":[8],"potentiality":[9],"in":[10,94],"vision":[11,32,114,148,166],"tasks.":[12],"However,":[13],"the":[14,19,23,29,41,45,51,59,84,119,165,177,192,196],"split":[15,99],"fixed-size":[16,100],"patches":[17,132,155],"divide":[18],"input":[20],"features":[21],"into":[22],"same":[24],"size":[25],"patches,":[26,55,101],"which":[27,56,87,125,150],"ignores":[28],"fact":[30],"that":[31,110],"elements":[33],"are":[34],"often":[35],"various":[36,113],"and":[37,159,173],"thus":[38],"may":[39],"destroy":[40],"semantic":[42,174],"information.":[43,139],"Also,":[44],"vanilla":[46],"transformer":[48],"cannot":[49],"guarantee":[50],"information":[52,63,109,129],"communication":[53,128],"between":[54],"will":[57],"prevent":[58],"extraction":[60],"of":[61,156,168,179,195],"attention":[62,108,138],"with":[64,98],"a":[65,143],"global":[66,137],"view.":[67],"To":[68],"circumvent":[69],"those":[70],"problems,":[71],"we":[72,81,117,141,184],"propose":[73,83,142],"an":[74,89],"Efficient":[75],"Attention":[76],"Pyramid":[77],"Transformer":[78],"(EAPT).":[79],"Specifically,":[80],"first":[82],"Deformable":[85],"Attention,":[86],"learns":[88],"offset":[90],"for":[91,147,154],"each":[92],"position":[93,144],"patches.":[95],"Thus,":[96],"even":[97],"our":[102,180],"method":[103],"can":[104,111,126,151],"still":[105],"obtain":[106,127],"non-fixed":[107],"cover":[112],"elements.":[115],"Then,":[116],"design":[118],"Encode-Decode":[120],"Communication":[121],"module":[122],"(En-DeC":[123],"module),":[124],"among":[130],"all":[131],"to":[133,190],"get":[134],"more":[135],"complete":[136],"Finally,":[140],"encoding":[145],"specifically":[146],"transformers,":[149],"be":[152],"used":[153],"any":[157,160],"dimension":[158],"length.":[161],"Extensive":[162],"experiments":[163],"on":[164],"tasks":[167],"image":[169],"classification,":[170],"object":[171],"detection,":[172],"segmentation":[175],"demonstrate":[176],"effectiveness":[178],"proposed":[181,197],"model.":[182],"Furthermore,":[183],"also":[185],"conduct":[186],"rigorous":[187],"ablation":[188],"studies":[189],"evaluate":[191],"key":[193],"components":[194],"structure.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":104},{"year":2025,"cited_by_count":228},{"year":2024,"cited_by_count":216},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":6}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}