{"id":"https://openalex.org/W3091353327","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206932","title":"Multi-level Visual Fusion Networks for Image Captioning","display_name":"Multi-level Visual Fusion Networks for Image Captioning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3091353327","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206932","mag":"3091353327"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5069672411","display_name":"Dongming Zhou","orcid":"https://orcid.org/0000-0003-0139-9415"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongming Zhou","raw_affiliation_strings":["Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, GuiLin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, GuiLin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016469515","display_name":"Canlong Zhang","orcid":"https://orcid.org/0000-0003-4375-1405"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Canlong Zhang","raw_affiliation_strings":["Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, GuiLin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, GuiLin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701695","display_name":"Zhixin Li","orcid":"https://orcid.org/0000-0002-5313-6134"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Li","raw_affiliation_strings":["Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, GuiLin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, GuiLin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006288178","display_name":"Zhiwen Wang","orcid":"https://orcid.org/0000-0003-2309-7282"},"institutions":[{"id":"https://openalex.org/I18570673","display_name":"Guangxi University of Science and Technology","ror":"https://ror.org/02fj6b627","country_code":"CN","type":"education","lineage":["https://openalex.org/I18570673"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwen Wang","raw_affiliation_strings":["College of Computer Science and Communications Engineering, Guangxi University of Science and Technology, Liuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Communications Engineering, Guangxi University of Science and Technology, Liuzhou, China","institution_ids":["https://openalex.org/I18570673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996999979019165,"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":0.9923999905586243,"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":0.9091256856918335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8489370942115784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6183463335037231},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5610522627830505},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5347855091094971},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5335092544555664},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45291516184806824},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4236217141151428},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4193084239959717},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36512723565101624}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9091256856918335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8489370942115784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6183463335037231},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5610522627830505},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5347855091094971},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5335092544555664},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45291516184806824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4236217141151428},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4193084239959717},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36512723565101624},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2607151106","https://openalex.org/W2729842244","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2885013662","https://openalex.org/W2949376505","https://openalex.org/W2962918138","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963248296","https://openalex.org/W2963403868","https://openalex.org/W2963635623","https://openalex.org/W2969679616","https://openalex.org/W2972897806","https://openalex.org/W3103022576","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6630875275","https://openalex.org/W6639102338","https://openalex.org/W6685322675","https://openalex.org/W6739901393","https://openalex.org/W6741068176","https://openalex.org/W6755631863","https://openalex.org/W6756147243"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"is":[2,93,121],"a":[3,49],"multi-modal":[4],"complex":[5],"task":[6],"in":[7,16,39,117],"machine":[8],"learning.":[9,58],"Traditional":[10],"methods":[11],"focus":[12],"only":[13],"on":[14,56,114,135],"entities":[15,27],"visual":[17,51,61,72,78,100,128],"strategy":[18,41,62,101,106,110,119],"networks,":[19],"and":[20,28,36,92,103,139,142,149],"can't":[21],"reason":[22],"about":[23],"the":[24,60,88,96,99,104,136,144,147,150],"relationship":[25],"between":[26,98],"attributes.":[29],"There":[30],"are":[31,68],"problems":[32],"of":[33,77,127,146,152],"exposure":[34],"bias":[35],"error":[37],"accumulation":[38],"language":[40,105,118],"networks.":[42,130],"To":[43],"this":[44,46],"end,":[45],"paper":[47],"proposes":[48],"multi-level":[50,64],"fusion":[52,81,129],"network":[53,66,82,102],"model":[54,134,148,153,159],"based":[55,113],"reinforcement":[57,115],"In":[59],"network,":[63],"neural":[65],"modules":[67],"used":[69,94,122],"to":[70,123],"transform":[71],"features":[73],"into":[74],"feature":[75],"sets":[76],"knowledge.":[79],"The":[80,108],"generates":[83],"function":[84],"words":[85],"that":[86],"make":[87],"description":[89],"more":[90],"fluent,":[91],"for":[95],"interaction":[97],"network.":[107],"self-criticism":[109],"gradient":[111],"algorithm":[112],"learning":[116,154],"networks":[120],"achieve":[124],"end-to-end":[125],"optimization":[126],"We":[131],"evaluated":[132],"our":[133],"Flickr":[137],"30K":[138],"MS-COCO":[140],"datasets,":[141],"verified":[143],"accuracy":[145],"diversity":[151],"subtitles":[155],"through":[156],"experiments.":[157],"Our":[158],"achieves":[160],"better":[161],"performance":[162],"over":[163],"state-of-the-art":[164],"methods.":[165]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}