{"id":"https://openalex.org/W3206600220","doi":"https://doi.org/10.1145/3474085.3475708","title":"RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection","display_name":"RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206600220","doi":"https://doi.org/10.1145/3474085.3475708","mag":"3206600220"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475708","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.12130","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhuofan Zong","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuofan Zong","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qianggang Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianggang Cao","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":null,"display_name":"Biao Leng","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Leng","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.1462,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.86529571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5637","last_page":"5645"},"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":0.9973999857902527,"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":0.9950000047683716,"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":0.8773000240325928},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.805400013923645},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6740000247955322},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6018999814987183},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5126000046730042},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5055999755859375},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49470001459121704},{"id":"https://openalex.org/keywords/feature-detection","display_name":"Feature detection (computer vision)","score":0.44279998540878296}],"concepts":[{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.8773000240325928},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.805400013923645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7488999962806702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7148000001907349},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6740000247955322},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49470001459121704},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48919999599456787},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.44279998540878296},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3490999937057495},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2858999967575073},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3475708","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2110.12130","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.12130","pdf_url":"https://arxiv.org/pdf/2110.12130","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.12130","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.12130","pdf_url":"https://arxiv.org/pdf/2110.12130","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1849277567","https://openalex.org/W2565639579","https://openalex.org/W2601564443","https://openalex.org/W2888728082","https://openalex.org/W2899607431","https://openalex.org/W2922438466","https://openalex.org/W2934198733","https://openalex.org/W2962721361","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963299996","https://openalex.org/W2963351448","https://openalex.org/W2963844898","https://openalex.org/W2963849369","https://openalex.org/W2963857746","https://openalex.org/W2964093967","https://openalex.org/W2964241181","https://openalex.org/W2964444661","https://openalex.org/W2982619380","https://openalex.org/W2982770724","https://openalex.org/W2986357608","https://openalex.org/W2988452521","https://openalex.org/W2989604896","https://openalex.org/W2990152177","https://openalex.org/W3012573144","https://openalex.org/W3034307881","https://openalex.org/W3034427487","https://openalex.org/W3034496491","https://openalex.org/W3034971973","https://openalex.org/W3035316790","https://openalex.org/W3035396860","https://openalex.org/W3035473155","https://openalex.org/W3107473354","https://openalex.org/W3108849448","https://openalex.org/W3109381875","https://openalex.org/W3175630421","https://openalex.org/W4250482878"],"related_works":[],"abstract_inverted_index":{"Feature":[0,109],"pyramid":[1,75,81,127],"networks":[2],"(FPN)":[3],"are":[4,31,70,83],"widely":[5],"exploited":[6],"for":[7,24],"multi-scale":[8,142],"feature":[9,26,47,74,121],"fusion":[10,88,122],"in":[11,52,72,90],"existing":[12],"advanced":[13],"object":[14],"detection":[15,36],"frameworks.":[16],"Numerous":[17],"previous":[18],"works":[19],"have":[20],"developed":[21],"various":[22],"structures":[23,45],"bidirectional":[25,120,126],"fusion,":[27],"all":[28],"of":[29,107],"which":[30,56,105,179],"shown":[32],"to":[33,49,123,134,140,176],"improve":[34],"the":[35,62,73,86,125,149],"performance":[37,201],"effectively.":[38],"We":[39],"observe":[40],"that":[41],"these":[42,96],"complicated":[43],"network":[44],"require":[46],"pyramids":[48],"be":[50],"stacked":[51],"a":[53,91,100,203],"fixed":[54],"order,":[55],"introduces":[57],"longer":[58],"pipelines":[59],"and":[60,112,137,163],"reduces":[61],"inference":[63,128],"speed.":[64],"Moreover,":[65],"semantics":[66],"from":[67],"non-adjacent":[68,138],"levels":[69,82,139],"diluted":[71],"since":[76],"only":[77],"features":[78,143],"at":[79],"adjacent":[80,136],"merged":[84],"by":[85,186],"local":[87,119],"operation":[89],"sequence":[92],"manner.":[93],"To":[94],"address":[95],"issues,":[97],"we":[98],"propose":[99],"novel":[101],"architecture":[102],"named":[103],"RCNet,":[104],"consists":[106],"Reverse":[108],"Pyramid":[110],"(RevFP)":[111],"Cross-scale":[113],"Shift":[114],"Network":[115],"(CSN).":[116],"RevFP":[117],"utilizes":[118],"simplify":[124],"pipeline.":[129],"CSN":[130],"directly":[131],"propagates":[132],"representations":[133],"both":[135,161],"enable":[141],"more":[144],"correlative.":[145],"Extensive":[146],"experiments":[147],"on":[148],"MS":[150],"COCO":[151,194],"dataset":[152],"demonstrate":[153],"RCNet":[154,196],"can":[155,197],"consistently":[156],"bring":[157],"significant":[158],"improvements":[159],"over":[160],"one-stage":[162],"two-stage":[164],"detectors":[165],"with":[166,189,202],"subtle":[167],"extra":[168],"computational":[169],"overhead.":[170],"In":[171],"particular,":[172],"RetinaNet":[173],"is":[174,180],"boosted":[175],"40.2":[177],"AP,":[178],"3.7":[181],"points":[182],"higher":[183],"than":[184],"baseline,":[185],"replacing":[187],"FPN":[188],"our":[190],"proposed":[191],"model.":[192],"On":[193],"test-dev,":[195],"achieve":[198],"very":[199],"competitive":[200],"single-model":[204],"single-scale":[205],"50.5":[206],"AP.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2021-10-25T00:00:00"}