{"id":"https://openalex.org/W2977731412","doi":"https://doi.org/10.1109/ijcnn.2019.8851721","title":"Image Captioning with Partially Rewarded Imitation Learning","display_name":"Image Captioning with Partially Rewarded Imitation Learning","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2977731412","doi":"https://doi.org/10.1109/ijcnn.2019.8851721","mag":"2977731412"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8851721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","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/A5060542294","display_name":"Xintong Yu","orcid":"https://orcid.org/0000-0002-4916-671X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xintong Yu","raw_affiliation_strings":["State Key Lab of Intelligent Technologies and Systems Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence, Tsinghua University (THUAI), Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Intelligent Technologies and Systems Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence, Tsinghua University (THUAI), Beijing, P.R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000013167","display_name":"Tszhang Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tszhang Guo","raw_affiliation_strings":["State Key Lab of Intelligent Technologies and Systems Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence, Tsinghua University (THUAI), Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Intelligent Technologies and Systems Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence, Tsinghua University (THUAI), Beijing, P.R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101956475","display_name":"Kun Fu","orcid":"https://orcid.org/0000-0002-2305-1017"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Fu","raw_affiliation_strings":["State Key Lab of Intelligent Technologies and Systems Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence, Tsinghua University (THUAI), Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Intelligent Technologies and Systems Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence, Tsinghua University (THUAI), Beijing, P.R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440394","display_name":"Lei Li","orcid":"https://orcid.org/0000-0003-1959-1683"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["State Key Lab of Intelligent Technologies and Systems Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence, Tsinghua University (THUAI), Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Intelligent Technologies and Systems Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence, Tsinghua University (THUAI), Beijing, P.R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065063835","display_name":"Changshui Zhang","orcid":"https://orcid.org/0000-0002-8088-367X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changshui Zhang","raw_affiliation_strings":["State Key Lab of Intelligent Technologies and Systems Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence, Tsinghua University (THUAI), Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Intelligent Technologies and Systems Beijing National Research Center for Information Science and Technology (BNRist), Institute for Artificial Intelligence, Tsinghua University (THUAI), Beijing, P.R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100326967","display_name":"Jianwei Zhang","orcid":"https://orcid.org/0000-0002-5491-1745"},"institutions":[{"id":"https://openalex.org/I4210136595","display_name":"Hamburg Institut (Germany)","ror":"https://ror.org/03t0n2419","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210136595"]},{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jianwei Zhang","raw_affiliation_strings":["Department of Informatics, Universitat\u00a8 Hamburg, Institute of Technical Aspects of Multimodal Systems (TAMS), Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Universitat\u00a8 Hamburg, Institute of Technical Aspects of Multimodal Systems (TAMS), Hamburg, Germany","institution_ids":["https://openalex.org/I4210136595","https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5060542294"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.1012,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44408594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9983999729156494,"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":0.9901000261306763,"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":0.9608484506607056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8047608137130737},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.781160295009613},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7170586585998535},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7069963216781616},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6518361568450928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6316260099411011},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5970988869667053},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5259770750999451},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.49065080285072327},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48691022396087646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.446450412273407},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4337879717350006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38734832406044006},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36489754915237427}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9608484506607056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047608137130737},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.781160295009613},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7170586585998535},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7069963216781616},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6518361568450928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6316260099411011},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5970988869667053},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5259770750999451},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.49065080285072327},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48691022396087646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.446450412273407},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4337879717350006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38734832406044006},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36489754915237427},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8851721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1999874108","https://openalex.org/W2061562262","https://openalex.org/W2064675550","https://openalex.org/W2075567596","https://openalex.org/W2098774185","https://openalex.org/W2099471712","https://openalex.org/W2105103432","https://openalex.org/W2112796928","https://openalex.org/W2113023245","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2512434509","https://openalex.org/W2558533273","https://openalex.org/W2564590796","https://openalex.org/W2604178507","https://openalex.org/W2616969219","https://openalex.org/W2951824008","https://openalex.org/W2962968835","https://openalex.org/W2963014947","https://openalex.org/W2963033554","https://openalex.org/W2963084599","https://openalex.org/W2963248296","https://openalex.org/W2963248348","https://openalex.org/W2963277051","https://openalex.org/W2963373786","https://openalex.org/W2963448089","https://openalex.org/W2963877622","https://openalex.org/W2964018924","https://openalex.org/W2964121744","https://openalex.org/W2964201867","https://openalex.org/W2964268978","https://openalex.org/W3101313921","https://openalex.org/W4320013936","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6685322675","https://openalex.org/W6713055699","https://openalex.org/W6718092244","https://openalex.org/W6718379498","https://openalex.org/W6725318829","https://openalex.org/W6727862155","https://openalex.org/W6730485539","https://openalex.org/W6730522037","https://openalex.org/W6730719754","https://openalex.org/W6732249622","https://openalex.org/W6738090124","https://openalex.org/W6785694401","https://openalex.org/W6898505805"],"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/W2995777218"],"abstract_inverted_index":{"Current":[0],"state-of-the-art":[1],"image":[2,77],"captioning":[3,78],"algorithms":[4],"have":[5],"achieved":[6],"great":[7],"progress":[8],"via":[9],"reinforcement":[10],"learning":[11],"or":[12,43],"generative":[13],"adversarial":[14,31,118],"nets,":[15],"with":[16,58,95],"hand-craft":[17],"metrics":[18,42,66],"such":[19],"as":[20,22],"CIDEr":[21,114],"the":[23,26,35,38,49,91,104,111,126,131],"reward":[24,93],"for":[25,34,76],"former":[27],"and":[28,61,86,115],"signals":[29],"from":[30,48,56,117],"discriminative":[32],"networks":[33],"latter.":[36],"Despite":[37],"high":[39],"scores":[40],"on":[41,65,121,143],"improvement":[44],"in":[45,102],"diversity":[46],"gained":[47],"application":[50],"of":[51,63,81,113,133],"these":[52],"methods,":[53],"they":[54],"suffer":[55],"distinction":[57],"human-written":[59],"sentences":[60],"drop":[62],"ratings":[64],"respectively.In":[67],"this":[68],"paper,":[69],"we":[70,98],"propose":[71],"a":[72],"novel":[73],"training":[74],"objective":[75],"that":[79,125],"consists":[80],"two":[82],"parts":[83],"representing":[84],"explicit":[85],"implicit":[87],"knowledge":[88],"respectively.":[89],"Optimizing":[90],"new":[92],"partially":[94],"imitation":[96],"learning,":[97],"devise":[99],"an":[100],"algorithm":[101],"which":[103],"caption":[105],"generator":[106],"is":[107],"trained":[108],"to":[109],"maximize":[110],"combination":[112],"predictions":[116],"discriminator.":[119],"Experiments":[120],"MSCOCO":[122],"dataset":[123],"demonstrate":[124],"proposed":[127],"method":[128],"can":[129],"integrate":[130],"strengths":[132],"state-of-the-arts,":[134],"producing":[135],"more":[136],"human-like":[137],"captions":[138],"while":[139],"maintaining":[140],"comparable":[141],"performance":[142],"traditional":[144],"metrics.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}