{"id":"https://openalex.org/W4402351508","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650584","title":"Image Caption Method from Coarse to Fine Based On Dual Encoder-Decoder Framework","display_name":"Image Caption Method from Coarse to Fine Based On Dual Encoder-Decoder Framework","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351508","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650584"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650584","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5107925226","display_name":"Zefeng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zefeng Li","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108097210","display_name":"Yuehu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehu Liu","raw_affiliation_strings":["Xi’an Jiaotong University,College of Artificial Intelligence,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,College of Artificial Intelligence,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110814145","display_name":"Yonghong Song","orcid":"https://orcid.org/0000-0001-5978-3781"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Song","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107925226"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14223906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","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":0.9994999766349792,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.7577038407325745},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6934024095535278},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6892864108085632},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.439175546169281},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4369547367095947},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4225679337978363},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.359944224357605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34412115812301636},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.154097318649292},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08149141073226929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577038407325745},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6934024095535278},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6892864108085632},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.439175546169281},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4369547367095947},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4225679337978363},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.359944224357605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34412115812301636},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.154097318649292},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08149141073226929},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650584","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":40,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2112912048","https://openalex.org/W2130942839","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2184997678","https://openalex.org/W2220981600","https://openalex.org/W2302086703","https://openalex.org/W2481240925","https://openalex.org/W2550553598","https://openalex.org/W2558834163","https://openalex.org/W2575842049","https://openalex.org/W2600463316","https://openalex.org/W2745461083","https://openalex.org/W2949376505","https://openalex.org/W2963084599","https://openalex.org/W2964018924","https://openalex.org/W2964253311","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3103022576","https://openalex.org/W3167939936","https://openalex.org/W3203790606","https://openalex.org/W4237040408","https://openalex.org/W4288329833","https://openalex.org/W6630875275","https://openalex.org/W6639118148","https://openalex.org/W6676647902","https://openalex.org/W6678262379","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6686505396","https://openalex.org/W6763643401"],"related_works":["https://openalex.org/W3203142394","https://openalex.org/W4390516098","https://openalex.org/W2161474341","https://openalex.org/W4302615923","https://openalex.org/W2181948922","https://openalex.org/W1974101135","https://openalex.org/W2351061015","https://openalex.org/W2384362569","https://openalex.org/W2017509870","https://openalex.org/W2352553236"],"abstract_inverted_index":{"Encoders":[0],"are":[1,29],"widely":[2],"used":[3],"in":[4,155],"the":[5,11,15,22,25,34,41,67,125,164,169,173,181],"field":[6],"of":[7,96,113,208],"image":[8,17,35,48,73,77,97,102,127,145,170,201],"caption,":[9],"but":[10],"statements":[12,28],"generated":[13,26],"by":[14,134],"current":[16],"caption":[18,49,176,184,202],"method":[19,50,198],"may":[20],"miss":[21],"target":[23],"and":[24,62,65,83,93,98,117,158,172,179,204,212],"description":[27],"not":[30],"appropriate":[31],"enough":[32],"for":[33,60],"content.":[36],"In":[37,142],"order":[38],"to":[39,69,136,151],"solve":[40],"above":[42],"problems,":[43],"we":[44],"propose":[45],"a":[46,58,71,105,114,118,138,206],"coarse-fine":[47],"based":[51,80],"on":[52,81,191],"dual":[53,106],"encoder-decoder":[54,107,116,122,166],"framework,":[55],"which":[56,88,111,131],"provides":[57],"mechanism":[59],"discovering":[61],"correcting":[63],"omissions":[64],"enables":[66],"model":[68],"generate":[70],"complete":[72],"description.":[74,141],"Firstly,":[75],"an":[76,144],"feature":[78,146,161,171],"extractor":[79],"global":[82,91],"local":[84,94],"information":[85,92,95,187],"is":[86,109,132,149],"designed,":[87,110],"can":[89],"extract":[90],"obtain":[99],"more":[100],"abundant":[101],"representation.":[103],"Secondly,":[104],"framework":[108],"consists":[112],"coarse-grained":[115],"fine-grained":[119,165,183],"encoder-decoder.":[120],"Coarse-grained":[121],"requires":[123],"only":[124],"original":[126],"features":[128],"as":[129,177],"input,":[130,178],"processed":[133],"transformer":[135],"produce":[137],"coarse":[139,156,174],"text":[140,157,175],"addition,":[143],"auto-enhancement":[147],"module":[148],"proposed":[150,197],"detect":[152],"missing":[153],"objects":[154],"enhance":[159],"their":[160],"expression.":[162],"Finally,":[163],"uses":[167],"both":[168],"generates":[180],"final":[182],"after":[185],"multi-modal":[186],"fusion.":[188],"Experimental":[189],"results":[190],"MSCOCO":[192],"datasets":[193],"show":[194],"that":[195],"our":[196],"outperforms":[199],"previous":[200],"methods":[203],"achieves":[205],"performance":[207],"39.7":[209],"BLEU-4":[210],"score":[211],"121.6":[213],"CIDEr-A":[214],"score.":[215]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}