{"id":"https://openalex.org/W4384664514","doi":"https://doi.org/10.1109/tip.2023.3251693","title":"Rethinking Attentive Object Detection via Neural Attention Learning","display_name":"Rethinking Attentive Object Detection via Neural Attention Learning","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384664514","doi":"https://doi.org/10.1109/tip.2023.3251693","pmid":"https://pubmed.ncbi.nlm.nih.gov/37463088"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3251693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3251693","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","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/A5030551813","display_name":"Chongjian Ge","orcid":"https://orcid.org/0000-0003-1142-9171"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chongjian Ge","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, China","Department of Computer Science, University of Hong Kong, Pokfulam, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-1142-9171","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science, University of Hong Kong, Pokfulam, Hong Kong, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068034476","display_name":"Yibing Song","orcid":"https://orcid.org/0000-0003-3667-531X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibing Song","raw_affiliation_strings":["AI3 Institute, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3667-531X","affiliations":[{"raw_affiliation_string":"AI3 Institute, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704678","display_name":"Chao Ma","orcid":"https://orcid.org/0000-0002-8459-2845"},"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":"Chao Ma","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8459-2845","affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070842891","display_name":"Yuankai Qi","orcid":"https://orcid.org/0000-0003-4312-5682"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuankai Qi","raw_affiliation_strings":["Australian Institute for Machine Learning, The University of Adelaide, Adelaide, SA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning, The University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100752686","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0002-6685-7950"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, China","Department of Computer Science, University of Hong Kong, Pokfulam, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-6685-7950","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science, University of Hong Kong, Pokfulam, Hong Kong, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0845,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.93379275,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"33","issue":null,"first_page":"1726","last_page":"1739"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9991999864578247,"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":0.9977999925613403,"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":0.7876089811325073},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7544618844985962},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.7469437718391418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7338640689849854},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6902973651885986},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5360878109931946},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5265610218048096},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5070774555206299},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.506266713142395},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4797881245613098},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4453997313976288},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4424852132797241},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4406878650188446},{"id":"https://openalex.org/keywords/backbone-network","display_name":"Backbone network","score":0.4287857413291931},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42050012946128845},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15051871538162231}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876089811325073},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7544618844985962},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.7469437718391418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7338640689849854},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6902973651885986},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5360878109931946},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5265610218048096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5070774555206299},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.506266713142395},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4797881245613098},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4453997313976288},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4424852132797241},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4406878650188446},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.4287857413291931},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42050012946128845},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15051871538162231},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3251693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3251693","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:37463088","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37463088","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1993229407","https://openalex.org/W2031489346","https://openalex.org/W2036989445","https://openalex.org/W2080849219","https://openalex.org/W2102605133","https://openalex.org/W2105101328","https://openalex.org/W2108598243","https://openalex.org/W2109255472","https://openalex.org/W2112594540","https://openalex.org/W2144764737","https://openalex.org/W2193145675","https://openalex.org/W2217433794","https://openalex.org/W2295107390","https://openalex.org/W2421627342","https://openalex.org/W2490270993","https://openalex.org/W2497039038","https://openalex.org/W2561238782","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2585123518","https://openalex.org/W2607037079","https://openalex.org/W2610871254","https://openalex.org/W2729222819","https://openalex.org/W2752782242","https://openalex.org/W2769291631","https://openalex.org/W2779380177","https://openalex.org/W2779991293","https://openalex.org/W2792643794","https://openalex.org/W2799166040","https://openalex.org/W2948375907","https://openalex.org/W2950800384","https://openalex.org/W2955058313","https://openalex.org/W2962721361","https://openalex.org/W2962851944","https://openalex.org/W2962858109","https://openalex.org/W2963037989","https://openalex.org/W2963082988","https://openalex.org/W2963113370","https://openalex.org/W2963150697","https://openalex.org/W2963321359","https://openalex.org/W2963351448","https://openalex.org/W2963481014","https://openalex.org/W2963516811","https://openalex.org/W2963727135","https://openalex.org/W2964038557","https://openalex.org/W2964080601","https://openalex.org/W2964269771","https://openalex.org/W2981420411","https://openalex.org/W2987151592","https://openalex.org/W2988916019","https://openalex.org/W2990792015","https://openalex.org/W2991403827","https://openalex.org/W3018757597","https://openalex.org/W3035524459","https://openalex.org/W3035729912","https://openalex.org/W3092462694","https://openalex.org/W3096609285","https://openalex.org/W3097055324","https://openalex.org/W3106250896","https://openalex.org/W3107867277","https://openalex.org/W3165924482","https://openalex.org/W4288281368","https://openalex.org/W4289752563","https://openalex.org/W4293584584","https://openalex.org/W4309299128","https://openalex.org/W4320002812","https://openalex.org/W6629368666","https://openalex.org/W6684191040","https://openalex.org/W6685133223","https://openalex.org/W6730179637","https://openalex.org/W6740374193","https://openalex.org/W6745637532","https://openalex.org/W6749029207","https://openalex.org/W6750227808","https://openalex.org/W6754805553","https://openalex.org/W6766313662","https://openalex.org/W6784094891","https://openalex.org/W6784923365","https://openalex.org/W6786026227"],"related_works":["https://openalex.org/W4376620596","https://openalex.org/W3177249605","https://openalex.org/W2534152068","https://openalex.org/W3138508047","https://openalex.org/W1972515067","https://openalex.org/W1689909837","https://openalex.org/W4293054914","https://openalex.org/W4298525700","https://openalex.org/W2953362004","https://openalex.org/W2549121492"],"abstract_inverted_index":{"Visual":[0],"attention":[1,82,99,186],"advances":[2,230],"object":[3,10,25,144,233],"detection":[4,26,113,145],"by":[5],"attending":[6],"neural":[7],"networks":[8],"to":[9,18,71,80,90,115,141,176,183,187],"representations.":[11],"While":[12],"existing":[13],"methods":[14],"incorporate":[15],"empirical":[16],"modules":[17],"empower":[19],"network":[20,29,93,136,159],"attention,":[21],"we":[22,55,96,125],"rethink":[23],"attentive":[24,130],"from":[27,203],"the":[28,49,58,62,66,72,88,91,98,111,142,167,173,181,188,195,226,231],"learning":[30,128],"perspective":[31],"in":[32,118,127,206],"this":[33,123,193],"work.":[34],"We":[35,75,138,164],"propose":[36],"a":[37,152,156,162],"NEural":[38],"Attention":[39],"Learning":[40],"approach":[41],"(NEAL)":[42],"which":[43,106,147],"consists":[44],"of":[45,51,65,151],"two":[46],"parts.":[47],"During":[48],"back-propagation":[50],"each":[52,204],"training":[53],"iteration,":[54],"first":[56],"calculate":[57],"partial":[59,78],"derivatives":[60,79],"(a.k.a.":[61],"accumulated":[63],"gradients)":[64],"classification":[67,200],"output":[68],"with":[69,110],"respect":[70],"input":[73],"features.":[74],"refine":[76],"these":[77],"obtain":[81],"response":[83,100],"maps":[84,101],"whose":[85],"elements":[86],"reflect":[87],"contributions":[89],"final":[92],"predictions.":[94],"Then,":[95],"formulate":[97],"as":[102],"extra":[103],"objective":[104],"functions,":[105],"are":[107,148],"combined":[108],"together":[109],"original":[112],"loss":[114],"train":[116],"detectors":[117],"an":[119,129],"end-to-end":[120],"manner.":[121],"In":[122],"way,":[124],"succeed":[126],"CNN":[131,153],"model":[132],"without":[133],"introducing":[134],"additional":[135],"structures.":[137],"apply":[139],"NEAL":[140,169,228],"two-stage":[143,232],"frameworks,":[146],"usually":[149],"composed":[150],"feature":[154],"backbone,":[155],"region":[157],"proposal":[158],"(RPN),":[160],"and":[161,199,220],"classifier.":[163],"show":[165],"that":[166,225],"proposed":[168,208,227],"not":[170],"only":[171],"helps":[172],"RPN":[174],"attend":[175],"objects":[177],"but":[178],"also":[179],"enables":[180],"classifier":[182],"pay":[184],"more":[185],"premier":[189],"positive":[190],"samples.":[191],"To":[192],"end,":[194],"localization":[196],"(proposal":[197],"generation)":[198],"mutually":[201],"benefit":[202],"other":[205],"our":[207],"method.":[209],"Extensive":[210],"experiments":[211],"on":[212],"large-scale":[213],"benchmark":[214],"datasets,":[215],"including":[216],"MS":[217],"COCO":[218],"2017":[219],"Pascal":[221],"VOC":[222],"2012,":[223],"demonstrate":[224],"algorithm":[229],"detector":[234],"over":[235],"state-of-the-art":[236],"approaches.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}