{"id":"https://openalex.org/W2987327987","doi":"https://doi.org/10.1109/tmm.2019.2951226","title":"Show, Tell, and Polish: Ruminant Decoding for Image Captioning","display_name":"Show, Tell, and Polish: Ruminant Decoding for Image Captioning","publication_year":2019,"publication_date":"2019-11-04","ids":{"openalex":"https://openalex.org/W2987327987","doi":"https://doi.org/10.1109/tmm.2019.2951226","mag":"2987327987"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2951226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2951226","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-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/A5040424302","display_name":"Longteng Guo","orcid":"https://orcid.org/0000-0002-4340-4000"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longteng Guo","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108392430","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-0903-9131"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062965702","display_name":"Shichen Lu","orcid":"https://orcid.org/0000-0002-1272-8723"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shichen Lu","raw_affiliation_strings":["School of Computing, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computing, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100511737","display_name":"Hanqing Lu","orcid":"https://orcid.org/0000-0001-9506-3407"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanqing Lu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040424302"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":4.3954,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.95656561,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"22","issue":"8","first_page":"2149","last_page":"2162"},"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":0.9921000003814697,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9891999959945679,"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":0.9241167306900024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8049700856208801},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7476173639297485},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6418513059616089},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5919720530509949},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5477021932601929},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.495395302772522},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.47134870290756226},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4272494614124298},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3682985305786133},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34416139125823975},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24311086535453796},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12691521644592285}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9241167306900024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8049700856208801},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7476173639297485},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6418513059616089},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5919720530509949},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5477021932601929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.495395302772522},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.47134870290756226},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4272494614124298},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3682985305786133},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34416139125823975},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24311086535453796},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12691521644592285},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2019.2951226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2951226","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.699999988079071,"id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G1117215680","display_name":null,"funder_award_id":"61872366","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8706534421","display_name":null,"funder_award_id":"61922086","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W658020064","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1902237438","https://openalex.org/W1905882502","https://openalex.org/W1923211482","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2079735306","https://openalex.org/W2101105183","https://openalex.org/W2119717200","https://openalex.org/W2130942839","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2163605009","https://openalex.org/W2176263492","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2564590796","https://openalex.org/W2575842049","https://openalex.org/W2613718673","https://openalex.org/W2618530766","https://openalex.org/W2729842244","https://openalex.org/W2740118378","https://openalex.org/W2745461083","https://openalex.org/W2754689878","https://openalex.org/W2754927243","https://openalex.org/W2795151422","https://openalex.org/W2885013662","https://openalex.org/W2887585070","https://openalex.org/W2890531016","https://openalex.org/W2890718122","https://openalex.org/W2895420168","https://openalex.org/W2902170865","https://openalex.org/W2903343986","https://openalex.org/W2906314281","https://openalex.org/W2962706528","https://openalex.org/W2962760898","https://openalex.org/W2963084599","https://openalex.org/W2963170456","https://openalex.org/W2963201326","https://openalex.org/W2963248296","https://openalex.org/W2963403868","https://openalex.org/W2963448089","https://openalex.org/W2963686907","https://openalex.org/W2964049455","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W3099884890","https://openalex.org/W3105136412","https://openalex.org/W4214717370","https://openalex.org/W4241811150","https://openalex.org/W4385245566","https://openalex.org/W6621543089","https://openalex.org/W6621906925","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6631516269","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6685322675","https://openalex.org/W6729046916","https://openalex.org/W6739901393","https://openalex.org/W6741068176","https://openalex.org/W6744684495","https://openalex.org/W6898505805"],"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/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2749708282"],"abstract_inverted_index":{"The":[0],"encoder-decoder":[1],"framework":[2,36,117,167],"has":[3],"been":[4],"the":[5,15,20,43,53,58,63,80,85,92,98,105,131,134,140,145,149,165,170],"base":[6,124],"of":[7,97,133,148,164,173],"popular":[8],"image":[9,23,121],"captioning":[10,116],"models,":[11],"which":[12,118],"typically":[13],"predicts":[14],"target":[16],"sentence":[17],"based":[18,182,208],"on":[19,186],"encoded":[21],"source":[22],"one":[24],"word":[25,77],"at":[26],"a":[27,33,114,123,127,178],"time":[28],"in":[29,42,109,152],"sequence.":[30],"However,":[31],"such":[32],"single-pass":[34,59,206],"decoding":[35,198,207],"encounters":[37],"two":[38,107,187],"problems.":[39],"First,":[40],"mistakes":[41],"predicted":[44],"words":[45,146,175],"cannot":[46,61],"be":[47],"corrected":[48],"and":[49,95,126,168,191,210],"may":[50],"propagate":[51],"to":[52,73,79,103,143,155],"entire":[54],"sentence.":[55,100],"Second,":[56],"because":[57],"decoder":[60,136],"access":[62],"following":[64],"un-generated":[65],"words,":[66,82],"it":[67],"can":[68,200],"only":[69],"perform":[70],"local":[71],"planning":[72,87],"choose":[74],"every":[75],"single":[76],"according":[78],"preceding":[81],"while":[83],"lacks":[84],"global":[86,141],"ability":[88],"as":[89,139],"for":[90],"maintaining":[91],"semantic":[93],"consistency":[94],"fluency":[96],"whole":[99,166],"In":[101],"order":[102],"address":[104],"above":[106],"problems,":[108],"this":[110],"work,":[111],"we":[112],"design":[113],"ruminant":[115,128,197],"contains":[119],"an":[120,153],"encoder,":[122],"decoder,":[125,151],"decoder.":[129],"Specifically,":[130],"outputs":[132],"former/base":[135],"are":[137],"utilized":[138],"information":[142],"guide":[144],"prediction":[147],"latter/ruminant":[150],"attempt":[154],"mimic":[156],"human":[157],"polishing":[158],"process.":[159],"We":[160],"enable":[161],"jointly":[162],"training":[163],"overcome":[169],"non-differential":[171],"problem":[172],"discrete":[174],"by":[176],"designing":[177],"novel":[179],"reinforcement":[180],"learning":[181],"optimization":[183],"algorithm.":[184],"Experiments":[185],"datasets":[188],"(MS":[189],"COCO":[190],"Flickr30":[192],"k)":[193],"demonstrate":[194],"that":[195],"our":[196],"method":[199],"bring":[201],"significant":[202],"improvements":[203],"over":[204],"traditional":[205],"models":[209],"achieves":[211],"state-of-the-art":[212],"performance.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}