{"id":"https://openalex.org/W2938603906","doi":"https://doi.org/10.1109/tpami.2019.2909864","title":"Context-Aware Visual Policy Network for Fine-Grained Image Captioning","display_name":"Context-Aware Visual Policy Network for Fine-Grained Image Captioning","publication_year":2019,"publication_date":"2019-12-05","ids":{"openalex":"https://openalex.org/W2938603906","doi":"https://doi.org/10.1109/tpami.2019.2909864","mag":"2938603906","pmid":"https://pubmed.ncbi.nlm.nih.gov/30969916"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2019.2909864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2019.2909864","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/1906.02365","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424059","display_name":"Daqing Liu","orcid":"https://orcid.org/0000-0002-8286-0105"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daqing Liu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103150943","display_name":"Feng Wu","orcid":"https://orcid.org/0000-0001-7266-5579"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003217535"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":9.1967,"has_fulltext":false,"cited_by_count":155,"citation_normalized_percentile":{"value":0.98317893,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"44","issue":"2","first_page":"710","last_page":"722"},"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":0.9901999831199646,"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":0.9883000254631042,"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/closed-captioning","display_name":"Closed captioning","score":0.9656343460083008},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.810912013053894},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.629001796245575},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6179866790771484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6087560057640076},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.5641324520111084},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.556769073009491},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.510765552520752},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5058014392852783},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3342137336730957},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3065422773361206},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17206573486328125}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9656343460083008},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810912013053894},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.629001796245575},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6179866790771484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6087560057640076},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.5641324520111084},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.556769073009491},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.510765552520752},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5058014392852783},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3342137336730957},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3065422773361206},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17206573486328125},{"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006736","descriptor_name":"Horses","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006736","descriptor_name":"Horses","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006736","descriptor_name":"Horses","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1109/tpami.2019.2909864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2019.2909864","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:30969916","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30969916","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 pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:1906.02365","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.02365","pdf_url":"https://arxiv.org/pdf/1906.02365","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"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/162628","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/162628","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.02365","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.02365","pdf_url":"https://arxiv.org/pdf/1906.02365","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":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2988286480","display_name":null,"funder_award_id":"2017YFB1300201","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4530701113","display_name":null,"funder_award_id":"WK2100100030","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5276383603","display_name":null,"funder_award_id":"61622211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6197875348","display_name":null,"funder_award_id":"61620106009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8290336390","display_name":null,"funder_award_id":"61525206","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W1983927101","https://openalex.org/W1996430422","https://openalex.org/W2004131797","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2105482032","https://openalex.org/W2117539524","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2123301721","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2163605009","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2471094925","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2549599535","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2563399268","https://openalex.org/W2575842049","https://openalex.org/W2579549467","https://openalex.org/W2591644541","https://openalex.org/W2605045867","https://openalex.org/W2607151106","https://openalex.org/W2613718673","https://openalex.org/W2618530766","https://openalex.org/W2729842244","https://openalex.org/W2737766105","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2764024122","https://openalex.org/W2890585349","https://openalex.org/W2949376505","https://openalex.org/W2950178297","https://openalex.org/W2950761309","https://openalex.org/W2962706528","https://openalex.org/W2962716332","https://openalex.org/W2962764817","https://openalex.org/W2963084599","https://openalex.org/W2963224792","https://openalex.org/W2963248296","https://openalex.org/W2963305465","https://openalex.org/W2963758027","https://openalex.org/W2964121744","https://openalex.org/W2964268978","https://openalex.org/W2964308564","https://openalex.org/W3103022576","https://openalex.org/W4214717370","https://openalex.org/W4230563027","https://openalex.org/W4241811150","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638742206","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6685322675","https://openalex.org/W6741068176"],"related_works":["https://openalex.org/W2391800119","https://openalex.org/W2595239241","https://openalex.org/W2799181378","https://openalex.org/W2052919063","https://openalex.org/W3003711649","https://openalex.org/W2904173691","https://openalex.org/W4365517254","https://openalex.org/W270947280","https://openalex.org/W3009270862","https://openalex.org/W2017877785"],"abstract_inverted_index":{"With":[0],"the":[1,22,51,61,127,153,162,167,172,226],"maturity":[2],"of":[3,24,53,228,245],"visual":[4,13,58,83,90,107,155,174,179,187,197,247],"detection":[5],"techniques,":[6],"we":[7,29,129],"are":[8,30,93],"more":[9,37],"ambitious":[10],"in":[11,32],"describing":[12],"content":[14],"with":[15,68],"open-vocabulary,":[16],"fine-grained":[17,38,138],"and":[18,36,40,85,106,144,159,206,235,242],"free-form":[19],"language,":[20],"i.e.,":[21],"task":[23,52],"image":[25,43,73,141,145,203],"captioning.":[26,147],"In":[27],"particular,":[28],"interested":[31],"generating":[33,118],"longer,":[34],"richer":[35],"sentences":[39],"paragraphs":[41],"as":[42,99,122,157],"descriptions.":[44],"Image":[45],"captioning":[46,74,143,204,237],"can":[47,193],"be":[48,212],"translated":[49],"to":[50,88,195],"sequential":[54],"language":[55,66,79,209],"prediction":[56],"given":[57,171],"content,":[59],"where":[60],"output":[62],"sequence":[63],"forms":[64],"natural":[65],"description":[67],"plausible":[69],"grammar.":[70],"However,":[71],"existing":[72],"methods":[75],"focus":[76],"only":[77,183],"on":[78,233],"policy":[80,210,220],"while":[81],"not":[82],"policy,":[84],"thus":[86],"fail":[87],"capture":[89],"context":[91,163],"that":[92,182],"crucial":[94],"for":[95,137,166],"compositional":[96],"reasoning":[97],"such":[98,121],"object":[100],"relationships":[101],"(e.g.,":[102,109],"\"man":[103],"riding":[104],"horse\")":[105],"comparisons":[108],"\"small(er)":[110],"cat\").":[111],"This":[112],"issue":[113],"is":[114,164],"especially":[115],"severe":[116],"when":[117],"longer":[119],"sequences":[120],"a":[123,131,185],"paragraph.":[124],"To":[125],"fill":[126],"gap,":[128],"propose":[130],"Context-Aware":[132],"Visual":[133],"Policy":[134],"network":[135],"(CAVP)":[136],"image-to-language":[139],"generation:":[140],"sentence":[142],"paragraph":[146],"During":[148],"captioning,":[149],"CAVP":[150,192,229],"explicitly":[151],"considers":[152],"previous":[154],"attentions":[156],"context,":[158],"decides":[160],"whether":[161],"used":[165],"current":[168,173],"word/sentence":[169],"generation":[170],"attention.":[175],"Compared":[176],"against":[177],"traditional":[178],"attention":[180],"mechanism":[181],"fixes":[184],"single":[186],"region":[188],"at":[189],"each":[190],"step,":[191],"attend":[194],"complex":[196],"compositions":[198],"over":[199],"time.":[200],"The":[201],"whole":[202],"model-CAVP":[205],"its":[207],"subsequent":[208],"network-can":[211],"efficiently":[213],"optimized":[214],"end-to-end":[215],"by":[216,230],"using":[217,239],"an":[218],"actor-critic":[219],"gradient":[221],"method.":[222],"We":[223],"have":[224],"demonstrated":[225],"effectiveness":[227],"state-of-the-art":[231],"performances":[232],"MS-COCO":[234],"Stanford":[236],"datasets,":[238],"various":[240],"metrics":[241],"sensible":[243],"visualizations":[244],"qualitative":[246],"context.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":31},{"year":2019,"cited_by_count":6}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}