{"id":"https://openalex.org/W2995482434","doi":"https://doi.org/10.1109/tip.2019.2957850","title":"HAR-Net: Joint Learning of Hybrid Attention for Single-Stage Object Detection","display_name":"HAR-Net: Joint Learning of Hybrid Attention for Single-Stage Object Detection","publication_year":2019,"publication_date":"2019-12-12","ids":{"openalex":"https://openalex.org/W2995482434","doi":"https://doi.org/10.1109/tip.2019.2957850","mag":"2995482434","pmid":"https://pubmed.ncbi.nlm.nih.gov/31831414"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2019.2957850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2019.2957850","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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.11141","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ya-Li Li","orcid":"https://orcid.org/0000-0002-6629-7228"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ya-Li Li","raw_affiliation_strings":["Department of Electrical Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shengjin Wang","orcid":"https://orcid.org/0000-0001-7809-1932"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengjin Wang","raw_affiliation_strings":["Department of Electrical Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.839,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.88959125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"3092","last_page":"3103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9527000188827515,"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":0.9527000188827515,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0031999999191612005,"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":0.002899999963119626,"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/object-detection","display_name":"Object detection","score":0.8072999715805054},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5906999707221985},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.557200014591217},{"id":"https://openalex.org/keywords/object-class-detection","display_name":"Object-class detection","score":0.5259000062942505},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5110999941825867},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5109999775886536},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48069998621940613},{"id":"https://openalex.org/keywords/viola\u2013jones-object-detection-framework","display_name":"Viola\u2013Jones object detection framework","score":0.4666999876499176},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.428600013256073}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.8072999715805054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728999853134155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7472000122070312},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5906999707221985},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5885999798774719},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.557200014591217},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.5259000062942505},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5110999941825867},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5109999775886536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48069998621940613},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.4666999876499176},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4235999882221222},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.38929998874664307},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.36039999127388},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3573000133037567},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.289900004863739},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.27149999141693115}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2019.2957850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2019.2957850","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:31831414","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31831414","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},{"id":"pmh:oai:arXiv.org:1904.11141","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.11141","pdf_url":"https://arxiv.org/pdf/1904.11141","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:1904.11141","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.11141","pdf_url":"https://arxiv.org/pdf/1904.11141","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://openalex.org/G2647066567","display_name":null,"funder_award_id":"61771288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8235566811","display_name":null,"funder_award_id":"61701277","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1903029394","https://openalex.org/W2016215417","https://openalex.org/W2088049833","https://openalex.org/W2102605133","https://openalex.org/W2106248527","https://openalex.org/W2136705357","https://openalex.org/W2147800946","https://openalex.org/W2155893237","https://openalex.org/W2168356304","https://openalex.org/W2194775991","https://openalex.org/W2474309084","https://openalex.org/W2550553598","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2592939477","https://openalex.org/W2601564443","https://openalex.org/W2741727820","https://openalex.org/W2745461083","https://openalex.org/W2752782242","https://openalex.org/W2768489488","https://openalex.org/W2801086478","https://openalex.org/W2891894830","https://openalex.org/W2897054934","https://openalex.org/W2961553857","https://openalex.org/W2962850830","https://openalex.org/W2963037989","https://openalex.org/W2963113370","https://openalex.org/W2963150162","https://openalex.org/W2963150697","https://openalex.org/W2963299996","https://openalex.org/W2963351448","https://openalex.org/W2963495494","https://openalex.org/W2963516811","https://openalex.org/W2963899050","https://openalex.org/W2964121718","https://openalex.org/W2964241181","https://openalex.org/W6600313631","https://openalex.org/W6630875275","https://openalex.org/W6639102338","https://openalex.org/W6653248861","https://openalex.org/W6684191040","https://openalex.org/W6692004142","https://openalex.org/W6703941868","https://openalex.org/W6714138976","https://openalex.org/W6717137822","https://openalex.org/W6731615698","https://openalex.org/W6732243160","https://openalex.org/W6739901393","https://openalex.org/W6745637532","https://openalex.org/W6749954789","https://openalex.org/W6750227808","https://openalex.org/W6751325469","https://openalex.org/W6752378368","https://openalex.org/W6785652829"],"related_works":[],"abstract_inverted_index":{"Object":[0],"detection":[1,18,142,154],"has":[2,13,26],"been":[3,14],"a":[4,37,162],"challenging":[5],"task":[6],"in":[7,16],"computer":[8],"vision.":[9],"Although":[10],"significant":[11],"progress":[12],"made":[15],"object":[17,43,60,128,170],"with":[19,67,81,95],"deep":[20],"neural":[21],"networks,":[22],"the":[23,48,82,100,109,116,123,134,140,153,158],"attention":[24,39,54,57,79,92,104,111,118,131,149],"mechanism":[25,40,80],"yet":[27],"to":[28,73,107],"be":[29],"fully":[30],"developed.":[31],"In":[32,62],"this":[33],"paper,":[34],"we":[35,46],"propose":[36,122],"hybrid":[38,110,117,148],"for":[41,58,127],"single-stage":[42,59,125,169],"detection.":[44,61,129],"First,":[45],"present":[47],"modules":[49,132],"of":[50,103],"spatial":[51,75],"attention,":[52],"channel":[53,78],"and":[55,86,121,133,156],"aligned":[56],"particular,":[63],"dilated":[64],"convolution":[65],"layers":[66],"symmetrically":[68],"fixed":[69],"rates":[70],"are":[71,105,137],"stacked":[72],"learn":[74],"attention.":[76],"A":[77],"cross-level":[83],"group":[84],"normalization":[85],"squeeze-and-excitation":[87],"operation":[88],"is":[89,93],"proposed.":[90],"Aligned":[91],"constructed":[94],"organized":[96],"deformable":[97],"filters.":[98],"Second,":[99],"three":[101],"types":[102],"unified":[106],"construct":[108],"mechanism.":[112],"We":[113],"then":[114],"plug":[115],"into":[119],"Retina-Net":[120],"efficient":[124],"HAR-Net":[126,136,159],"The":[130,144],"proposed":[135],"evaluated":[138],"on":[139],"COCO":[141],"dataset.":[143],"experiments":[145],"demonstrate":[146],"that":[147,157],"can":[150,160],"significantly":[151],"improve":[152],"accuracy":[155],"achieve":[161],"state-of-the-art":[163],"45.8%":[164],"mAP,":[165],"thus":[166],"outperforming":[167],"existing":[168],"detectors.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2019-12-26T00:00:00"}