{"id":"https://openalex.org/W2949792119","doi":"https://doi.org/10.18653/v1/p19-1652","title":"Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning","display_name":"Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2949792119","doi":"https://doi.org/10.18653/v1/p19-1652","mag":"2949792119"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1652","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1652","pdf_url":"https://www.aclweb.org/anthology/P19-1652.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1652.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078689432","display_name":"Zhihao Fan","orcid":"https://orcid.org/0000-0002-9910-7937"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihao Fan","raw_affiliation_strings":["School of Data Science, Fudan University, China"],"affiliations":[{"raw_affiliation_string":"School of Data Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011504177","display_name":"Zhongyu Wei","orcid":"https://orcid.org/0000-0003-3789-8507"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyu Wei","raw_affiliation_strings":["School of Data Science, Fudan University, China"],"affiliations":[{"raw_affiliation_string":"School of Data Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440548","display_name":"Siyuan Wang","orcid":"https://orcid.org/0000-0002-5036-0608"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Wang","raw_affiliation_strings":["School of Data Science, Fudan University, China"],"affiliations":[{"raw_affiliation_string":"School of Data Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088834359","display_name":"Xuanjing Huang","orcid":"https://orcid.org/0000-0001-9197-9426"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","raw_affiliation_strings":["School of Computer Science, Fudan University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078689432"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.7368,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.8795025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6514","last_page":"6524"},"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":0.9980000257492065,"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":0.9930999875068665,"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":0.9402296543121338},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8264560699462891},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.8127397298812866},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6581692695617676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.621828019618988},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5993074178695679},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5777164101600647},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5634239315986633},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.47592952847480774},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47254419326782227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46436139941215515},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2100220024585724},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10445272922515869},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08963331580162048}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9402296543121338},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8264560699462891},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.8127397298812866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6581692695617676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.621828019618988},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5993074178695679},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5777164101600647},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5634239315986633},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.47592952847480774},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47254419326782227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46436139941215515},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2100220024585724},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10445272922515869},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08963331580162048},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1652","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1652","pdf_url":"https://www.aclweb.org/anthology/P19-1652.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1652","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1652","pdf_url":"https://www.aclweb.org/anthology/P19-1652.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2702356746","display_name":null,"funder_award_id":"61702","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4666185321","display_name":null,"funder_award_id":"16JC1420401","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G4918981142","display_name":null,"funder_award_id":"61751201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5069775644","display_name":null,"funder_award_id":"6175120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5167091242","display_name":null,"funder_award_id":"No. 1","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5848258319","display_name":null,"funder_award_id":"0 and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6058138561","display_name":null,"funder_award_id":", No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6142973028","display_name":null,"funder_award_id":"17JC1420200","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G7475107363","display_name":null,"funder_award_id":"16JC1420401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8863666567","display_name":null,"funder_award_id":"and No.","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"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949792119.pdf","grobid_xml":"https://content.openalex.org/works/W2949792119.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1694858705","https://openalex.org/W1706899115","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2101105183","https://openalex.org/W2105103432","https://openalex.org/W2116261113","https://openalex.org/W2117539524","https://openalex.org/W2123301721","https://openalex.org/W2142192571","https://openalex.org/W2150824314","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2250539671","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2558834163","https://openalex.org/W2560730294","https://openalex.org/W2561296180","https://openalex.org/W2575842049","https://openalex.org/W2600463316","https://openalex.org/W2624022918","https://openalex.org/W2745461083","https://openalex.org/W2775082024","https://openalex.org/W2808021740","https://openalex.org/W2825507547","https://openalex.org/W2952246170","https://openalex.org/W2952782394","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2963175879","https://openalex.org/W2963351776","https://openalex.org/W2963371447","https://openalex.org/W2964018924","https://openalex.org/W2964121744","https://openalex.org/W3016211260"],"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/W3217195652","https://openalex.org/W1997182898"],"abstract_inverted_index":{"Existing":[0],"research":[1],"for":[2,14,20,76,111],"visual":[3,95],"captioning":[4],"usually":[5],"employs":[6],"a":[7,12,18,83],"CNN-RNN":[8],"architecture":[9],"that":[10,72],"combines":[11],"CNN":[13],"image":[15,74],"encoding":[16],"with":[17],"RNN":[19,135],"caption":[21,79,112,139],"generation,":[22],"where":[23],"the":[24,29,34,42,51,58,90,108,116,122,127,130,134,138,149],"vocabulary":[25,71,91,110,124,131],"is":[26,86,160],"constructed":[27,109],"from":[28,41,121],"entire":[30],"training":[31,52],"dataset":[32],"as":[33],"decoding":[35],"space.":[36],"Such":[37],"approaches":[38],"typically":[39],"suffer":[40],"problem":[43],"of":[44,151],"generating":[45],"N-grams":[46],"which":[47],"occur":[48],"frequently":[49],"in":[50],"set":[53],"but":[54],"are":[55,103],"irrelevant":[56],"to":[57,67,88,106,118,155],"given":[59],"image.":[60],"To":[61],"tackle":[62],"this":[63],"problem,":[64],"we":[65],"propose":[66],"construct":[68,89],"an":[69],"image-grounded":[70,123],"leverages":[73],"semantics":[75],"more":[77],"effective":[78],"generation.":[80,113],"More":[81],"concretely,":[82],"two-step":[84],"approach":[85],"proposed":[87],"by":[92],"incorporating":[93],"both":[94],"information":[96,132],"and":[97,126],"relationships":[98],"among":[99],"words.":[100],"Two":[101],"strategies":[102],"then":[104],"explored":[105],"utilize":[107],"One":[114],"constrains":[115],"generator":[117],"select":[119],"words":[120],"only":[125],"other":[128],"integrates":[129],"into":[133],"cell":[136],"during":[137],"generation":[140],"process.":[141],"Experimental":[142],"results":[143],"on":[144,162],"two":[145],"public":[146],"datasets":[147],"show":[148],"effectiveness":[150],"our":[152],"framework":[153],"compared":[154],"state-of-the-art":[156],"models.":[157],"Our":[158],"code":[159],"available":[161],"Github":[163],"1":[164],".":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}