{"id":"https://openalex.org/W2981994675","doi":"https://doi.org/10.1145/3343031.3350996","title":"Unpaired Cross-lingual Image Caption Generation with Self-Supervised Rewards","display_name":"Unpaired Cross-lingual Image Caption Generation with Self-Supervised Rewards","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981994675","doi":"https://doi.org/10.1145/3343031.3350996","mag":"2981994675"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3350996","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350996","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/A5088459000","display_name":"Yuqing Song","orcid":"https://orcid.org/0000-0002-0246-4330"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuqing Song","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776086","display_name":"Shizhe Chen","orcid":"https://orcid.org/0000-0002-7313-9703"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shizhe Chen","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049155292","display_name":"Yida Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yida Zhao","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088459000"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":3.2693,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.93956304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"784","last_page":"792"},"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":0.9932000041007996,"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":0.9854000210762024,"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":0.9716265797615051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8386586904525757},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.7914490699768066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6358557343482971},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5997319221496582},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5534939765930176},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5482840538024902},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4858112335205078},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4598684012889862},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4396498501300812},{"id":"https://openalex.org/keywords/language-translation","display_name":"Language translation","score":0.4199729263782501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36965346336364746},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3228638768196106},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32031387090682983},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07609793543815613}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9716265797615051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8386586904525757},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.7914490699768066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6358557343482971},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5997319221496582},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5534939765930176},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5482840538024902},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4858112335205078},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4598684012889862},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4396498501300812},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.4199729263782501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36965346336364746},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3228638768196106},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32031387090682983},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07609793543815613},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3350996","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350996","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":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2133459682","https://openalex.org/W2220981600","https://openalex.org/W2293344577","https://openalex.org/W2302086703","https://openalex.org/W2620636291","https://openalex.org/W2652651782","https://openalex.org/W2740118378","https://openalex.org/W2745461083","https://openalex.org/W2749708282","https://openalex.org/W2887585070","https://openalex.org/W2903179935","https://openalex.org/W2904651132","https://openalex.org/W2950304420","https://openalex.org/W2952122856","https://openalex.org/W2963084599","https://openalex.org/W2963170456","https://openalex.org/W2963426402","https://openalex.org/W2963448089","https://openalex.org/W2963499204","https://openalex.org/W2964258722","https://openalex.org/W2966618235","https://openalex.org/W3102566412","https://openalex.org/W3105136412","https://openalex.org/W4206070857","https://openalex.org/W4299128829"],"related_works":["https://openalex.org/W2749708282","https://openalex.org/W2000013842","https://openalex.org/W4362495644","https://openalex.org/W2134714056","https://openalex.org/W4321065355","https://openalex.org/W2997015083","https://openalex.org/W3127743011","https://openalex.org/W2892009878","https://openalex.org/W3167690611","https://openalex.org/W4379381477"],"abstract_inverted_index":{"Generating":[0],"image":[1,33,42,93,148,160],"descriptions":[2],"in":[3,58,98,116,150],"different":[4],"languages":[5],"is":[6,14,28,50],"essential":[7],"to":[8,17,90,103,120,132],"satisfy":[9],"users":[10],"worldwide.":[11],"However,":[12,67],"it":[13],"prohibitively":[15],"expensive":[16],"collect":[18],"large-scale":[19],"paired":[20,55],"image-caption":[21,56],"dataset":[22],"for":[23,30,145],"every":[24],"target":[25,118],"language":[26,61,119],"which":[27,49],"critical":[29],"training":[31],"descent":[32],"captioning":[34,43,149],"models.":[35,66],"Previous":[36],"works":[37],"tackle":[38],"the":[39,52,59,76,99,117],"unpaired":[40,146],"cross-lingual":[41,92,147],"problem":[44],"through":[45],"a":[46,126],"pivot":[47,60],"language,":[48],"with":[51,95],"help":[53],"of":[54,108],"data":[57],"and":[62,81,124,136,153],"pivot-to-target":[63,77],"machine":[64],"translation":[65],"such":[68],"language-pivoted":[69],"approach":[70,165],"suffers":[71],"from":[72,113],"inaccuracy":[73],"brought":[74],"by":[75],"translation,":[78],"including":[79],"disfluency":[80],"visual":[82,128,138],"irrelevancy":[83],"errors.":[84,109],"In":[85],"this":[86],"paper,":[87],"we":[88],"propose":[89,125],"generate":[91],"captions":[94],"self-supervised":[96],"rewards":[97],"reinforcement":[100],"learning":[101],"framework":[102],"alleviate":[104],"these":[105],"two":[106,157],"types":[107],"We":[110,141],"employ":[111],"self-supervision":[112],"mono-lingual":[114],"corpus":[115],"provide":[121,133],"fluency":[122],"reward,":[123],"multi-level":[127],"semantic":[129],"matching":[130],"model":[131],"both":[134,151],"sentence-level":[135],"concept-level":[137],"relevancy":[139],"rewards.":[140],"conduct":[142],"extensive":[143],"experiments":[144],"English":[152],"Chinese":[154],"respectively":[155],"on":[156],"widely":[158],"used":[159],"caption":[161],"corpora.":[162],"The":[163],"proposed":[164],"achieves":[166],"significant":[167],"performance":[168],"improvement":[169],"over":[170],"state-of-the-art":[171],"methods.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}