{"id":"https://openalex.org/W2965846473","doi":"https://doi.org/10.1609/aaai.v33i01.33018320","title":"Deliberate Attention Networks for Image Captioning","display_name":"Deliberate Attention Networks for Image Captioning","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2965846473","doi":"https://doi.org/10.1609/aaai.v33i01.33018320","mag":"2965846473"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33018320","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018320","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4845/4718","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4845/4718","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041527073","display_name":"Kaixuan Fan","orcid":"https://orcid.org/0009-0003-0354-5057"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixuan Fan","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024067284","display_name":"Xianglong Liu","orcid":"https://orcid.org/0000-0001-8425-4195"},"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":"Xianglong Liu","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":49,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"8320","last_page":"8327"},"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":0.9868999719619751,"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":0.9796000123023987,"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":0.9806996583938599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7895214557647705},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7130112648010254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5682373046875},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5526328086853027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5230956077575684},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5130173563957214},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.49149763584136963},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.434388667345047},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4240260124206543},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3467881977558136}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9806996583938599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7895214557647705},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7130112648010254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5682373046875},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5526328086853027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5230956077575684},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5130173563957214},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.49149763584136963},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.434388667345047},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4240260124206543},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3467881977558136},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33018320","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018320","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4845/4718","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"},{"id":"pmh:oai:ojs.aaai.org:article/4845","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33018320","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018320","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4845/4718","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G6598207522","display_name":null,"funder_award_id":"ZYGX2014J063","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8167822162","display_name":null,"funder_award_id":"ZYGX2016J085","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965846473.pdf","grobid_xml":"https://content.openalex.org/works/W2965846473.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2542835211","https://openalex.org/W2552161745","https://openalex.org/W2560313346","https://openalex.org/W2575842049","https://openalex.org/W2597985671","https://openalex.org/W2613718673","https://openalex.org/W2621571501","https://openalex.org/W2742570236","https://openalex.org/W2745461083","https://openalex.org/W2752047430","https://openalex.org/W2791445206","https://openalex.org/W2799047197","https://openalex.org/W2807941860","https://openalex.org/W2884326683","https://openalex.org/W2895902247","https://openalex.org/W2949376505","https://openalex.org/W2950304420","https://openalex.org/W2951780762","https://openalex.org/W2953106684","https://openalex.org/W2962958773","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2963170456","https://openalex.org/W2963448089","https://openalex.org/W2964049455","https://openalex.org/W4294149591","https://openalex.org/W6682631176","https://openalex.org/W6687483927","https://openalex.org/W6698228248","https://openalex.org/W6729046916","https://openalex.org/W6729624334","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3045147787","https://openalex.org/W4320016117","https://openalex.org/W3044039333","https://openalex.org/W2547835662","https://openalex.org/W3183824823","https://openalex.org/W2966014552","https://openalex.org/W3008515501","https://openalex.org/W2923366293","https://openalex.org/W2890653670","https://openalex.org/W2965707726"],"abstract_inverted_index":{"In":[0,79],"daily":[1],"life,":[2],"deliberation":[3,59],"is":[4,38,127],"a":[5,84,109],"common":[6],"behavior":[7],"for":[8,32,92,107],"human":[9],"to":[10,47,52,71,150,165,203],"improve":[11],"or":[12],"refine":[13],"their":[14],"work":[15],"(e.g.,":[16],"writing,":[17],"reading":[18],"and":[19,50,65,104,139,162,169,182,188,200,208],"drawing).":[20],"To":[21],"date,":[22],"encoder-decoder":[23],"framework":[24,37],"with":[25,159],"attention":[26,67,98,106,120,141],"mechanisms":[27],"has":[28,147],"achieved":[29],"great":[30],"progress":[31],"image":[33,93],"captioning.":[34,94],"However,":[35],"such":[36],"in":[39,142],"essential":[40],"an":[41],"one-pass":[42],"forward":[43],"process":[44],"while":[45,115],"encoding":[46],"hidden":[48,63,102,137],"states":[49,64,103],"attending":[51],"visual":[53,66,105,140],"features,":[54],"but":[55],"lacks":[56],"of":[57,112],"the":[58,73,101,113,116,125,130,136,143,148,176,179,211],"action.":[60],"The":[61,95],"learned":[62],"are":[68],"directly":[69],"used":[70],"predict":[72],"final":[74],"captions":[75],"without":[76],"further":[77,155],"polishing.":[78],"this":[80],"paper,":[81],"we":[82],"present":[83],"novel":[85],"Deliberate":[86],"Residual":[87],"Attention":[88],"Network,":[89],"namely":[90],"DA,":[91],"first-pass":[96],"residual-based":[97,119],"layer":[99,121,138],"prepares":[100],"generating":[108],"preliminary":[110],"version":[111],"captions,":[114],"second-pass":[117,126],"deliberate":[118],"refines":[122],"them.":[123],"Since":[124],"based":[128],"on":[129,178,210],"rough":[131],"global":[132],"features":[133],"captured":[134],"by":[135],"first-pass,":[144],"our":[145,157],"DA":[146,158],"potential":[149],"generate":[151],"better":[152],"sentences.":[153],"We":[154],"equip":[156],"discriminative":[160],"loss":[161],"reinforcement":[163],"learning":[164],"disambiguate":[166],"image/caption":[167],"pairs":[168],"reduce":[170],"exposure":[171],"bias.":[172],"Our":[173],"model":[174],"improves":[175],"state-of-the-arts":[177],"MSCOCO":[180],"dataset":[181],"reaches":[183],"37.5%":[184],"BELU-4,":[185],"28.5%":[186],"METEOR":[187,199,207],"125.6%":[189],"CIDEr.":[190],"It":[191],"also":[192],"outperforms":[193],"the-state-ofthe-arts":[194],"from":[195],"25.1%":[196],"BLEU-4,":[197,205],"20.4%":[198],"53.1%":[201],"CIDEr":[202],"29.4%":[204],"23.0%":[206],"66.6%":[209],"Flickr30K":[212],"dataset.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}