{"id":"https://openalex.org/W3170952646","doi":"https://doi.org/10.1109/tcsvt.2021.3087002","title":"CATFPN: Adaptive Feature Pyramid With Scale-Wise Concatenation and Self-Attention","display_name":"CATFPN: Adaptive Feature Pyramid With Scale-Wise Concatenation and Self-Attention","publication_year":2021,"publication_date":"2021-06-08","ids":{"openalex":"https://openalex.org/W3170952646","doi":"https://doi.org/10.1109/tcsvt.2021.3087002","mag":"3170952646"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2021.3087002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3087002","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/A5100632698","display_name":"Jing Huang","orcid":"https://orcid.org/0000-0001-6365-5344"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Huang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-6365-5344","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065397399","display_name":"Zhenxue Chen","orcid":"https://orcid.org/0000-0001-9637-5170"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenxue Chen","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China","State Key Laboratory of Integrated Services Networks, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-9637-5170","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731724","display_name":"Q. M. Jonathan Wu","orcid":"https://orcid.org/0000-0002-5208-7975"},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Q. M. Jonathan Wu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5208-7975","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada","institution_ids":["https://openalex.org/I74413500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101798630","display_name":"Chengyun Liu","orcid":"https://orcid.org/0000-0001-5689-3950"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyun Liu","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China","School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071576848","display_name":"Hui Yuan","orcid":"https://orcid.org/0000-0001-5212-3393"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Yuan","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-5212-3393","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102826660","display_name":"Weikai He","orcid":"https://orcid.org/0000-0002-1246-1627"},"institutions":[{"id":"https://openalex.org/I4210099312","display_name":"Shandong Jiaotong University","ror":"https://ror.org/01848hk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weikai He","raw_affiliation_strings":["School of Aeronautics, Shandong Jiaotong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Aeronautics, Shandong Jiaotong University, Jinan, China","institution_ids":["https://openalex.org/I4210099312"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1306,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.79931594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"12","first_page":"8142","last_page":"8152"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9969000220298767,"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/pyramid","display_name":"Pyramid (geometry)","score":0.7839620113372803},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7474626302719116},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7214816808700562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7149581909179688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6617550849914551},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6487290859222412},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6382523775100708},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5232357382774353},{"id":"https://openalex.org/keywords/backbone-network","display_name":"Backbone network","score":0.4967861771583557},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48963862657546997},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43221622705459595},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4165356457233429},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3620433509349823},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12982669472694397}],"concepts":[{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.7839620113372803},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7474626302719116},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7214816808700562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7149581909179688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6617550849914551},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6487290859222412},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6382523775100708},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5232357382774353},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.4967861771583557},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48963862657546997},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43221622705459595},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4165356457233429},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3620433509349823},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12982669472694397},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2021.3087002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2021.3087002","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":[],"awards":[{"id":"https://openalex.org/G66036439","display_name":null,"funder_award_id":"Scip201801","funder_id":"https://openalex.org/F4320335669","funder_display_name":"Key Laboratory of System Control and Information Processing"},{"id":"https://openalex.org/G6943220726","display_name":null,"funder_award_id":"ISN20-06","funder_id":"https://openalex.org/F4320330485","funder_display_name":"State Key Laboratory of Integrated Services Networks"},{"id":"https://openalex.org/G867047861","display_name":null,"funder_award_id":"2019YFB1311001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8865734290","display_name":null,"funder_award_id":"61876099","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"},{"id":"https://openalex.org/F4320330485","display_name":"State Key Laboratory of Integrated Services Networks","ror":null},{"id":"https://openalex.org/F4320335669","display_name":"Key Laboratory of System Control and Information Processing","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W197865394","https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2109255472","https://openalex.org/W2115763357","https://openalex.org/W2144506857","https://openalex.org/W2147800946","https://openalex.org/W2151103935","https://openalex.org/W2163605009","https://openalex.org/W2168356304","https://openalex.org/W2186094539","https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2548197316","https://openalex.org/W2549139847","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2572745118","https://openalex.org/W2579985080","https://openalex.org/W2622263826","https://openalex.org/W2752782242","https://openalex.org/W2806331055","https://openalex.org/W2837605352","https://openalex.org/W2886335102","https://openalex.org/W2888728082","https://openalex.org/W2899607431","https://openalex.org/W2899771611","https://openalex.org/W2950800384","https://openalex.org/W2961553857","https://openalex.org/W2962721361","https://openalex.org/W2962917547","https://openalex.org/W2962922273","https://openalex.org/W2963037989","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963202462","https://openalex.org/W2963323244","https://openalex.org/W2963351448","https://openalex.org/W2963584620","https://openalex.org/W2963857746","https://openalex.org/W2964093967","https://openalex.org/W2964444661","https://openalex.org/W2966926453","https://openalex.org/W2982220924","https://openalex.org/W2982770724","https://openalex.org/W2991089415","https://openalex.org/W3035316790","https://openalex.org/W3106250896","https://openalex.org/W3121052081","https://openalex.org/W4288325606","https://openalex.org/W4293584584","https://openalex.org/W6620707391","https://openalex.org/W6639102338","https://openalex.org/W6684191040","https://openalex.org/W6714138976","https://openalex.org/W6731615698","https://openalex.org/W6732243160","https://openalex.org/W6739622702","https://openalex.org/W6750227808","https://openalex.org/W6753494528","https://openalex.org/W6756040250","https://openalex.org/W6764322716","https://openalex.org/W6765807774","https://openalex.org/W6771062828","https://openalex.org/W6785652829","https://openalex.org/W6788922626"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W3095575180","https://openalex.org/W2894651257","https://openalex.org/W2993564273","https://openalex.org/W4286907753","https://openalex.org/W3208389169","https://openalex.org/W3134004915","https://openalex.org/W3200590620","https://openalex.org/W4200172193","https://openalex.org/W4303926741"],"abstract_inverted_index":{"It":[0],"is":[1,81],"a":[2,85,94,130,134],"typical":[3,155],"problem":[4],"in":[5,19,154],"the":[6,35,49,52,71,126,138,152,176,186],"field":[7],"of":[8,51,73,103,189],"object":[9,25],"detection":[10],"to":[11,32,83,143],"simultaneously":[12],"detect":[13],"objects":[14],"with":[15,34],"large":[16],"scale":[17,36],"variation":[18],"one":[20],"image.":[21],"Recently":[22],"proposed":[23],"state-of-the-art":[24],"detectors":[26],"generally":[27],"learn":[28],"pyramidal":[29],"feature":[30,45,53,59,79,96,123,135],"representation":[31],"deal":[33],"variation,":[37],"which":[38],"has":[39],"been":[40],"proved":[41],"effective":[42],"via":[43],"various":[44],"pyramid":[46,54,80,97,136],"networks.":[47,76],"However,":[48],"majority":[50],"networks":[55],"based":[56,146],"on":[57,147,175,185],"heuristic":[58],"fusion":[60],"strategies":[61],"may":[62],"be":[63,141],"suboptimal,":[64],"as":[65],"excess":[66],"human":[67],"guidance":[68],"will":[69],"restrict":[70],"self-learning":[72],"deep":[74],"neural":[75],"An":[77],"adaptive":[78],"bound":[82],"provide":[84],"significant":[86],"performance":[87,183],"boost.":[88],"In":[89],"this":[90],"paper,":[91],"we":[92],"propose":[93],"novel":[95],"network":[98],"named":[99],"CATFPN":[100,139,153],"that":[101],"consists":[102],"Scale-Wise":[104],"Feature":[105],"Concatenation":[106],"(SWFC)":[107],"module":[108,116],"and":[109,125,157,164,169],"Global":[110],"Context":[111],"(GC)":[112],"block.":[113],"The":[114],"SWFC":[115],"evenly":[117],"distributes":[118],"semantic":[119],"features":[120],"for":[121],"each":[122],"layer":[124],"GC":[127],"block":[128],"introduces":[129],"self-attention":[131],"mechanism.":[132],"As":[133],"network,":[137],"can":[140],"applied":[142],"any":[144],"detector":[145,160],"multi-scale":[148],"features.":[149],"We":[150],"adopt":[151],"RetinaNet":[156],"Faster":[158],"R-CNN":[159],"models,":[161],"without":[162],"bells":[163],"whistles,":[165],"achieving":[166],"1.1%":[167],"AP":[168,171],"0.7%":[170],"improvements":[172],"over":[173],"FPN":[174],"MS":[177],"COCO":[178,190],"benchmark,":[179],"respectively.":[180],"Our":[181],"competitive":[182],"reported":[184],"test-dev":[187],"subset":[188],"achieves":[191],"42.3%":[192],"AP.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}