{"id":"https://openalex.org/W3035160838","doi":"https://doi.org/10.1109/cvpr42600.2020.01034","title":"Normalized and Geometry-Aware Self-Attention Network for Image Captioning","display_name":"Normalized and Geometry-Aware Self-Attention Network for Image Captioning","publication_year":2020,"publication_date":"2020-06-01","ids":{"openalex":"https://openalex.org/W3035160838","doi":"https://doi.org/10.1109/cvpr42600.2020.01034","mag":"3035160838"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr42600.2020.01034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr42600.2020.01034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-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/A5040424302","display_name":"Longteng Guo","orcid":"https://orcid.org/0000-0002-4340-4000"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longteng Guo","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108392430","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-0903-9131"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103047969","display_name":"Xinxin Zhu","orcid":"https://orcid.org/0000-0002-2142-5580"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxin Zhu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101964795","display_name":"Peng Yao","orcid":"https://orcid.org/0000-0003-0717-2836"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Yao","raw_affiliation_strings":["University of Science and Technology, Beijing"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology, Beijing","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062965702","display_name":"Shichen Lu","orcid":"https://orcid.org/0000-0002-1272-8723"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shichen Lu","raw_affiliation_strings":["Wuhan University"],"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100511737","display_name":"Hanqing Lu","orcid":"https://orcid.org/0000-0001-9506-3407"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanqing Lu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040424302"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":16.4872,"has_fulltext":false,"cited_by_count":255,"citation_normalized_percentile":{"value":0.99424801,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"10324","last_page":"10333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning 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/T11714","display_name":"Multimodal Machine Learning 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":0.9957000017166138,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.995199978351593,"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/closed-captioning","display_name":"Closed captioning","score":0.9766490459442139},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8181008696556091},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.7742835283279419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7457506060600281},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.570818305015564},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5199014544487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4983854293823242},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3546851575374603},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3332563042640686}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9766490459442139},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8181008696556091},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.7742835283279419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7457506060600281},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.570818305015564},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5199014544487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4983854293823242},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3546851575374603},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3332563042640686},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr42600.2020.01034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr42600.2020.01034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2139501017","https://openalex.org/W2154652894","https://openalex.org/W2171361956","https://openalex.org/W2463955103","https://openalex.org/W2502312327","https://openalex.org/W2506483933","https://openalex.org/W2613718673","https://openalex.org/W2737766105","https://openalex.org/W2800782462","https://openalex.org/W2804078698","https://openalex.org/W2887585070","https://openalex.org/W2896457183","https://openalex.org/W2903728819","https://openalex.org/W2933138175","https://openalex.org/W2949117887","https://openalex.org/W2955058313","https://openalex.org/W2962933664","https://openalex.org/W2963084599","https://openalex.org/W2963091558","https://openalex.org/W2963101956","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963524571","https://openalex.org/W2963560594","https://openalex.org/W2963652649","https://openalex.org/W2963925437","https://openalex.org/W2964067226","https://openalex.org/W2964080601","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W2965597639","https://openalex.org/W2966683369","https://openalex.org/W2971310675","https://openalex.org/W2981165461","https://openalex.org/W2986670728","https://openalex.org/W2987327987","https://openalex.org/W2989322838","https://openalex.org/W2996977542","https://openalex.org/W3002557610","https://openalex.org/W3103651098","https://openalex.org/W3105136412","https://openalex.org/W4288329833","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6679434410","https://openalex.org/W6682631176","https://openalex.org/W6685230081","https://openalex.org/W6724804524","https://openalex.org/W6739901393","https://openalex.org/W6740863234","https://openalex.org/W6746565888","https://openalex.org/W6749954789","https://openalex.org/W6752378368","https://openalex.org/W6755207826","https://openalex.org/W6761164592","https://openalex.org/W6763643401","https://openalex.org/W6766645339","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757"],"abstract_inverted_index":{"Self-attention":[0],"(SA)":[1],"network":[2],"has":[3],"shown":[4],"profound":[5],"value":[6],"in":[7,120],"image":[8,24,126,149],"captioning.":[9,25],"In":[10],"this":[11],"paper,":[12],"we":[13,27,52,97,129],"improve":[14],"SA":[15,35,107],"from":[16],"two":[17,132],"aspects":[18],"to":[19,67,77,88,108,137,159],"promote":[20],"the":[21,38,71,80,90,94,113,118,121,131,138,178],"performance":[22],"of":[23,34,40,83,93,101,180],"First,":[26],"propose":[28,98],"Normalized":[29],"Self-Attention":[30,103],"(NSA),":[31],"a":[32,54,99],"reparameterization":[33],"that":[36,60,85,105],"brings":[37],"benefits":[39],"normalization":[41,45,56],"inside":[42,74],"SA.":[43,75],"While":[44],"is":[46,62],"previously":[47],"only":[48],"applied":[49],"outside":[50],"SA,":[51],"introduce":[53],"novel":[55],"method":[57],"and":[58,65,110,134,152,173],"demonstrate":[59],"it":[61,69,86,136],"both":[63],"possible":[64],"beneficial":[66],"perform":[68],"on":[70,147,164],"hidden":[72],"activations":[73],"Second,":[76],"compensate":[78],"for":[79],"major":[81],"limit":[82],"Transformer":[84],"fails":[87],"model":[89],"geometry":[91,115],"structure":[92],"input":[95],"objects,":[96],"class":[100],"Geometry-aware":[102],"(GSA)":[104],"extends":[106],"explicitly":[109],"efficiently":[111],"consider":[112],"relative":[114],"relations":[116],"between":[117],"objects":[119],"image.":[122],"To":[123],"construct":[124],"our":[125,145,181],"captioning":[127,150],"model,":[128],"combine":[130],"modules":[133],"apply":[135],"vanilla":[139],"self-attention":[140],"network.":[141],"We":[142],"extensively":[143],"evaluate":[144],"proposals":[146],"MS-COCO":[148],"dataset":[151],"superior":[153],"results":[154],"are":[155],"achieved":[156],"when":[157],"comparing":[158],"state-of-the-art":[160],"approaches.":[161],"Further":[162],"experiments":[163],"three":[165],"challenging":[166],"tasks,":[167],"i.e.":[168],"video":[169],"captioning,":[170],"machine":[171],"translation,":[172],"visual":[174],"question":[175],"answering,":[176],"show":[177],"generality":[179],"methods.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":44},{"year":2023,"cited_by_count":48},{"year":2022,"cited_by_count":63},{"year":2021,"cited_by_count":52},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}