{"id":"https://openalex.org/W2982210816","doi":"https://doi.org/10.1145/3343031.3350961","title":"Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation","display_name":"Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2982210816","doi":"https://doi.org/10.1145/3343031.3350961","mag":"2982210816"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3350961","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","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/A5063603492","display_name":"Yadan Luo","orcid":"https://orcid.org/0000-0001-6272-2971"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Yadan Luo","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078170935","display_name":"Zi Huang","orcid":"https://orcid.org/0000-0002-9738-4949"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zi Huang","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459168","display_name":"Zheng Zhang","orcid":"https://orcid.org/0000-0003-1470-6998"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389369","display_name":"Ziwei Wang","orcid":"https://orcid.org/0000-0002-0107-7347"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ziwei Wang","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338386","display_name":"Jingjing Li","orcid":"https://orcid.org/0000-0002-5504-2529"},"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":"Jingjing Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chendu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chendu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"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":"Yang Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063603492"],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":2.8342,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.92912593,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2341","last_page":"2350"},"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":0.9936000108718872,"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":0.9825999736785889,"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/curiosity","display_name":"Curiosity","score":0.778153657913208},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7630921006202698},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.7627460956573486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7574688196182251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5889542102813721},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.550872802734375},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5233302116394043},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5078688263893127},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5074979662895203},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4593759775161743},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4151264429092407},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4005730152130127},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.18503355979919434},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1267232894897461},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09241285920143127},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07572764158248901}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.778153657913208},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7630921006202698},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.7627460956573486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7574688196182251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5889542102813721},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.550872802734375},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5233302116394043},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5078688263893127},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5074979662895203},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4593759775161743},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4151264429092407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4005730152130127},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.18503355979919434},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1267232894897461},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09241285920143127},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07572764158248901},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3350961","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2115613106","https://openalex.org/W2119717200","https://openalex.org/W2549599535","https://openalex.org/W2766237723","https://openalex.org/W2785543907","https://openalex.org/W2799185021","https://openalex.org/W2808663243","https://openalex.org/W2877093712","https://openalex.org/W2884326683","https://openalex.org/W2887712318","https://openalex.org/W2888020621","https://openalex.org/W2896124351","https://openalex.org/W2897964062","https://openalex.org/W2899771611","https://openalex.org/W2949376505","https://openalex.org/W2962968835","https://openalex.org/W2963033554","https://openalex.org/W2963177403","https://openalex.org/W2963523627","https://openalex.org/W3087871082","https://openalex.org/W3098077856","https://openalex.org/W3103022576","https://openalex.org/W4247950230"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W3094054656"],"abstract_inverted_index":{"Visual":[0],"paragraph":[1,74,128],"generation":[2],"aims":[3],"to":[4,59,96,103,169,173],"automatically":[5],"describe":[6],"a":[7,17,32,52,77,180],"given":[8],"image":[9],"from":[10,120,162,191],"different":[11],"perspectives":[12],"and":[13,42,64,81,112,178,213],"organize":[14],"sentences":[15],"in":[16,31,167,200],"coherent":[18],"way.":[19],"In":[20],"this":[21,29],"paper,":[22],"we":[23,50,131],"address":[24],"three":[25],"critical":[26],"challenges":[27],"for":[28,46,189],"task":[30],"reinforcement":[33],"learning":[34,186,190],"setting:":[35],"the":[36,39,43,62,67,73,83,92,117,126,145,151,163,171,197,206,211,216,220],"mode":[37],"collapse,":[38],"delayed":[40],"feedback,":[41],"time-consuming":[44,198],"warm-up":[45,199],"policy":[47,172],"networks.":[48],"Generally,":[49],"propose":[51],"novel":[53],"Curiosity-driven":[54],"Reinforcement":[55],"Learning":[56],"(CRL)":[57],"framework":[58],"jointly":[60],"enhance":[61],"diversity":[63],"accuracy":[65],"of":[66,86,215],"generated":[68],"paragraphs.":[69],"First,":[70],"by":[71,143,157,222],"modeling":[72],"captioning":[75],"as":[76,89],"long-term":[78],"decision-making":[79],"process":[80],"measuring":[82],"prediction":[84],"uncertainty":[85],"state":[87],"transitions":[88],"intrinsic":[90,159],"rewards,":[91],"model":[93],"is":[94,122,129,187],"incentivized":[95],"memorize":[97],"precise":[98],"but":[99],"rarely":[100],"spotted":[101],"descriptions":[102],"context,":[104],"rather":[105],"than":[106],"being":[107],"biased":[108],"towards":[109],"frequent":[110],"fragments":[111],"generic":[113],"patterns.":[114],"Second,":[115],"since":[116],"extrinsic":[118,153],"reward":[119],"evaluation":[121],"only":[123],"available":[124],"until":[125],"complete":[127],"generated,":[130],"estimate":[132],"its":[133],"expected":[134],"value":[135],"at":[136],"each":[137],"time":[138],"step":[139],"with":[140,225],"temporal-difference":[141],"learning,":[142],"considering":[144],"correlations":[146],"between":[147],"successive":[148],"actions.":[149],"Then":[150],"estimated":[152],"rewards":[154,160],"are":[155],"complemented":[156],"dense":[158],"produced":[161],"derived":[164],"curiosity":[165],"module,":[166],"order":[168],"encourage":[170],"fully":[174],"explore":[175],"action":[176],"space":[177],"find":[179],"global":[181],"optimum.":[182],"Third,":[183],"discounted":[184],"imitation":[185],"integrated":[188],"human":[192],"demonstrations,":[193],"without":[194],"separately":[195],"performing":[196],"advance.":[201],"Extensive":[202],"experiments":[203],"conducted":[204],"on":[205],"Standford":[207],"image-paragraph":[208],"dataset":[209],"demonstrate":[210],"effectiveness":[212],"efficiency":[214],"proposed":[217],"method,":[218],"improving":[219],"performance":[221],"38.4%":[223],"compared":[224],"state-of-the-art.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":12}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}