{"id":"https://openalex.org/W2904551248","doi":"https://doi.org/10.1609/aaai.v33i01.33018957","title":"Hierarchical Attention Network for Image Captioning","display_name":"Hierarchical Attention Network for Image Captioning","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2904551248","doi":"https://doi.org/10.1609/aaai.v33i01.33018957","mag":"2904551248"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33018957","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018957","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4924/4797","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4924/4797","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101609885","display_name":"Weixuan Wang","orcid":"https://orcid.org/0000-0003-4551-0795"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weixuan Wang","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430132","display_name":"Zhihong Chen","orcid":"https://orcid.org/0000-0002-9545-1327"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihong Chen","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056953478","display_name":"Haifeng Hu","orcid":"https://orcid.org/0000-0002-4884-323X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Hu","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101609885"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":9.063,"has_fulltext":true,"cited_by_count":129,"citation_normalized_percentile":{"value":0.97735192,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"33","issue":"01","first_page":"8957","last_page":"8964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning 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/T11714","display_name":"Multimodal Machine Learning 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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9825000166893005,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9474999904632568,"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":0.8684005737304688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8146717548370361},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6656622886657715},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6143923997879028},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5965832471847534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5640356540679932},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5200388431549072},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48605257272720337},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.48536741733551025},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4394344091415405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43772023916244507},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39878183603286743},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3838273584842682},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33519741892814636},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07537218928337097}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8684005737304688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8146717548370361},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6656622886657715},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6143923997879028},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5965832471847534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5640356540679932},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5200388431549072},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48605257272720337},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.48536741733551025},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4394344091415405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43772023916244507},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39878183603286743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3838273584842682},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33519741892814636},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07537218928337097},{"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/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33018957","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018957","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4924/4797","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33018957","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018957","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4924/4797","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5678804896","display_name":null,"funder_award_id":"61673402","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904551248.pdf","grobid_xml":"https://content.openalex.org/works/W2904551248.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W1968001820","https://openalex.org/W2116492146","https://openalex.org/W2154652894","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2412393473","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2558834163","https://openalex.org/W2560313346","https://openalex.org/W2575842049","https://openalex.org/W2607768201","https://openalex.org/W2616125804","https://openalex.org/W2729842244","https://openalex.org/W2745461083","https://openalex.org/W2794576774","https://openalex.org/W2796239628","https://openalex.org/W2949197413","https://openalex.org/W2949376505","https://openalex.org/W2962799512","https://openalex.org/W2963084599","https://openalex.org/W2963717374","https://openalex.org/W2964018924","https://openalex.org/W6639102338","https://openalex.org/W6639657675","https://openalex.org/W6642175321","https://openalex.org/W6666761814","https://openalex.org/W6682631176","https://openalex.org/W6687483927","https://openalex.org/W6698228248","https://openalex.org/W6715144786","https://openalex.org/W6728881024","https://openalex.org/W6741068176","https://openalex.org/W6749731246","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Recently,":[0],"attention":[1,13,43],"mechanism":[2],"has":[3],"been":[4],"successfully":[5],"applied":[6],"in":[7,178],"image":[8],"captioning,":[9],"but":[10],"the":[11,73,78,92,119,126,144,155,163,179],"existing":[12,127],"methods":[14],"are":[15],"only":[16],"established":[17],"on":[18,47,59,150],"low-level":[19],"spatial":[20],"features":[21,51,58,133],"or":[22],"high-level":[23],"text":[24],"features,":[25,82],"which":[26,63,140],"limits":[27],"richness":[28],"of":[29,50,57,81,121,170,176],"captions.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,112],"propose":[35],"a":[36,83,114,167,173],"Hierarchical":[37],"Attention":[38],"Network":[39],"(HAN)":[40],"that":[41,159],"enables":[42],"to":[44,69,77,90,101,117],"be":[45],"calculated":[46],"pyramidal":[48,54],"hierarchy":[49,55],"synchronously.":[52],"The":[53,97,146],"consists":[56],"diverse":[60],"semantic":[61],"levels,":[62],"allows":[64],"predicting":[65],"different":[66,70,79,109,122],"words":[67],"according":[68],"features.":[71,96,110,123],"On":[72],"other":[74],"hand,":[75],"due":[76],"modalities":[80],"Multivariate":[84],"Residual":[85],"Module":[86],"(MRM)":[87],"is":[88,99,148],"proposed":[89],"learn":[91],"joint":[93],"representations":[94],"from":[95],"MRM":[98],"able":[100],"model":[102,161],"projections":[103],"and":[104,134,154,172],"extract":[105],"relevant":[106],"relations":[107],"among":[108],"Furthermore,":[111],"introduce":[113],"context":[115],"gate":[116],"balance":[118],"contribution":[120],"Compared":[124],"with":[125],"methods,":[128,165],"our":[129,160],"approach":[130],"applies":[131],"hierarchical":[132],"exploits":[135],"several":[136],"multimodal":[137],"integration":[138],"strategies,":[139],"can":[141],"significantly":[142],"improve":[143],"performance.":[145],"HAN":[147],"verified":[149],"benchmark":[151],"MSCOCO":[152],"dataset,":[153],"experimental":[156],"results":[157],"indicate":[158],"outperforms":[162],"state-of-the-art":[164],"achieving":[166],"BLEU1":[168],"score":[169,175],"80.9":[171],"CIDEr":[174],"121.7":[177],"Karpathy\u2019s":[180],"test":[181],"split.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}