{"id":"https://openalex.org/W2887585070","doi":"https://doi.org/10.1145/3240508.3240632","title":"Context-Aware Visual Policy Network for Sequence-Level Image Captioning","display_name":"Context-Aware Visual Policy Network for Sequence-Level Image Captioning","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2887585070","doi":"https://doi.org/10.1145/3240508.3240632","mag":"2887585070"},"language":"en","primary_location":{"id":"doi:10.1145/3240508.3240632","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1808.05864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Daqing Liu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"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":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, 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":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"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":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"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/A5101424059"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":9.0409,"has_fulltext":false,"cited_by_count":121,"citation_normalized_percentile":{"value":0.98393855,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1416","last_page":"1424"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9897000193595886,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9883000254631042,"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":0.9495969414710999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8033228516578674},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6661986708641052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5595610737800598},{"id":"https://openalex.org/keywords/subsequence","display_name":"Subsequence","score":0.5257152915000916},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49586519598960876},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4298855662345886},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.42606738209724426},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4152151346206665},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35699203610420227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3263588547706604},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3214460611343384}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9495969414710999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8033228516578674},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6661986708641052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5595610737800598},{"id":"https://openalex.org/C137877099","wikidata":"https://www.wikidata.org/wiki/Q1332977","display_name":"Subsequence","level":3,"score":0.5257152915000916},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49586519598960876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4298855662345886},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.42606738209724426},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4152151346206665},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35699203610420227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3263588547706604},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3214460611343384},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3240508.3240632","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1808.05864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.05864","pdf_url":"https://arxiv.org/pdf/1808.05864","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:1808.05864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.05864","pdf_url":"https://arxiv.org/pdf/1808.05864","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":0.47999998927116394,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","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/W1996430422","https://openalex.org/W2004131797","https://openalex.org/W2064675550","https://openalex.org/W2101105183","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/W2312609093","https://openalex.org/W2471094925","https://openalex.org/W2481240925","https://openalex.org/W2506483933","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/W2600463316","https://openalex.org/W2607151106","https://openalex.org/W2613526370","https://openalex.org/W2618530766","https://openalex.org/W2729842244","https://openalex.org/W2737766105","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2767057417","https://openalex.org/W2768661419","https://openalex.org/W2949376505","https://openalex.org/W2950178297","https://openalex.org/W2950761309","https://openalex.org/W2951343884","https://openalex.org/W2952591111","https://openalex.org/W2953106684","https://openalex.org/W2962706528","https://openalex.org/W2962716332","https://openalex.org/W2962764817","https://openalex.org/W2963084599","https://openalex.org/W2963224792","https://openalex.org/W2963305465","https://openalex.org/W2964268978","https://openalex.org/W2964308564","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W4388002133","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Many":[0],"vision-language":[1],"tasks":[2],"can":[3,166,188],"be":[4,189],"reduced":[5],"to":[6,28,77,168,202],"the":[7,30,63,68,79,103,125,130,136,141,146,209],"problem":[8],"of":[9,211,229],"sequence":[10],"prediction":[11],"for":[12,85,113,124,140],"natural":[13],"language":[14,64,184],"output.":[15],"In":[16],"particular,":[17],"recent":[18],"advances":[19],"in":[20,39,46],"image":[21,57,115,160,176],"captioning":[22,58,177],"use":[23],"deep":[24],"reinforcement":[25],"learning":[26],"(RL)":[27],"alleviate":[29],"\"exposure":[31],"bias''":[32],"during":[33],"training:":[34],"ground-truth":[35],"subsequence":[36,51],"is":[37,52,138,235],"exposed":[38],"every":[40,118,163],"step":[41],"prediction,":[42],"which":[43],"introduces":[44],"bias":[45],"test":[47],"when":[48],"only":[49,60,156],"predicted":[50],"seen.":[53],"However,":[54],"existing":[55],"RL-based":[56],"methods":[59],"focus":[61],"on":[62,216],"policy":[65,70,185,197],"while":[66],"not":[67],"visual":[69,72,80,90,127,148,153,170,231],"(eg,":[71],"attention),":[73],"and":[74,96,132,181,220,226],"thus":[75],"fail":[76],"capture":[78],"context":[81,137],"that":[82,155],"are":[83],"crucial":[84],"compositional":[86],"reasoning":[87],"such":[88],"as":[89,129],"relationships":[91],"(\\eg,":[92],"\"man":[93],"riding":[94],"horse'')":[95],"comparisons":[97],"(eg.":[98],"\"smaller":[99],"cat\").":[100],"To":[101],"fill":[102],"gap,":[104],"we":[105],"propose":[106],"a":[107,158],"Context-Aware":[108],"Visual":[109],"Policy":[110],"network":[111,186],"(CAVP)":[112],"sequence-level":[114],"captioning.":[116],"At":[117],"time":[119],"step,":[120,164],"CAVP":[121,165,180,212],"explicitly":[122],"accounts":[123],"previous":[126],"attentions":[128],"context,":[131],"then":[133],"decides":[134],"whether":[135],"helpful":[139],"current":[142,147],"word":[143],"generation":[144],"given":[145],"attention.":[149],"Compared":[150],"against":[151],"traditional":[152],"attention":[154],"fixes":[157],"single":[159],"region":[161],"at":[162,237],"attend":[167],"complex":[169],"compositions":[171],"over":[172],"time.":[173],"The":[174,233],"whole":[175],"model":[178],"---":[179,187],"its":[182],"subsequent":[183],"efficiently":[190],"optimized":[191],"end-to-end":[192],"by":[193,213],"using":[194,223],"an":[195],"actor-critic":[196],"gradient":[198],"method":[199],"with":[200],"respect":[201],"any":[203],"caption":[204],"evaluation":[205],"metric.":[206],"We":[207],"demonstrate":[208],"effectiveness":[210],"state-of-the-art":[214],"performances":[215],"MS-COCO":[217],"offline":[218],"split":[219],"online":[221],"server,":[222],"various":[224],"metrics":[225],"sensible":[227],"visualizations":[228],"qualitative":[230],"context.":[232],"code":[234],"available":[236],"\\urlhttps://github.com/daqingliu/CAVP":[238]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":31},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":10}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}