{"id":"https://openalex.org/W2942914779","doi":"https://doi.org/10.1145/3310986.3311002","title":"The Role of Attention Mechanism and Multi-Feature in Image Captioning","display_name":"The Role of Attention Mechanism and Multi-Feature in Image Captioning","publication_year":2019,"publication_date":"2019-01-25","ids":{"openalex":"https://openalex.org/W2942914779","doi":"https://doi.org/10.1145/3310986.3311002","mag":"2942914779"},"language":"en","primary_location":{"id":"doi:10.1145/3310986.3311002","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3310986.3311002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","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/A5048526869","display_name":"Tien Dang","orcid":"https://orcid.org/0000-0001-6894-2852"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tien X. Dang","raw_affiliation_strings":["School of Electronics and Computer Engineering, Chonnam National University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Engineering, Chonnam National University, South Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026607867","display_name":"Aran Oh","orcid":null},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Aran Oh","raw_affiliation_strings":["School of Electronics and Computer Engineering, Chonnam National University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Engineering, Chonnam National University, South Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016894750","display_name":"In Seop Na","orcid":"https://orcid.org/0000-0001-6471-043X"},"institutions":[{"id":"https://openalex.org/I152238500","display_name":"Chosun University","ror":"https://ror.org/01zt9a375","country_code":"KR","type":"education","lineage":["https://openalex.org/I152238500"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"In-Seop Na","raw_affiliation_strings":["Software Convergence Education Institute, Chosun University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Convergence Education Institute, Chosun University, South Korea","institution_ids":["https://openalex.org/I152238500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100605822","display_name":"Soo-Hyung Kim","orcid":"https://orcid.org/0000-0003-3575-5035"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soo-Hyung Kim","raw_affiliation_strings":["School of Electronics and Computer Engineering, Chonnam National University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Engineering, Chonnam National University, South Korea","institution_ids":["https://openalex.org/I111277659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3051,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.59472184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"170","last_page":"174"},"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":0.9973000288009644,"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":0.9930999875068665,"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":0.9745974540710449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8757120370864868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7391943335533142},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6391406059265137},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5882180333137512},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5587702393531799},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.524752140045166},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5033051371574402},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.502535343170166},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4755803644657135},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4398488700389862},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4094170331954956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33108893036842346},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.059088438749313354}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9745974540710449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8757120370864868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7391943335533142},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6391406059265137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5882180333137512},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5587702393531799},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.524752140045166},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5033051371574402},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.502535343170166},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4755803644657135},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4398488700389862},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4094170331954956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33108893036842346},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.059088438749313354},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3310986.3311002","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3310986.3311002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2112912048","https://openalex.org/W2139380585","https://openalex.org/W2171361956","https://openalex.org/W2173180041","https://openalex.org/W2183341477","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2274287116","https://openalex.org/W2302086703","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2950178297","https://openalex.org/W2950577311","https://openalex.org/W2951583185","https://openalex.org/W2953022248","https://openalex.org/W2953158660","https://openalex.org/W2953276893","https://openalex.org/W2953322005","https://openalex.org/W2962739631","https://openalex.org/W3000226596","https://openalex.org/W3105531629","https://openalex.org/W4300939921"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W3008584592","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Up":[0],"to":[1,97,106,113],"now,":[2],"caption":[3],"generation":[4],"is":[5,39,58],"still":[6],"a":[7,14,21,40,78,128],"hard":[8],"problem":[9,25],"in":[10,43],"artificial":[11],"intelligence":[12],"where":[13,54],"textual":[15],"description":[16],"must":[17],"be":[18],"generated":[19],"for":[20,70],"given":[22,86],"image.":[23],"This":[24],"combines":[26],"both":[27],"computer":[28],"vision":[29],"and":[30,101,120,136],"natural":[31,82],"language":[32,83],"processing.":[33],"Generally,":[34],"the":[35,55,91,131],"CNN":[36],"-":[37],"RNN":[38],"popular":[41],"architecture":[42],"image":[44],"captioning.":[45],"Currently,":[46],"there":[47],"are":[48],"many":[49],"variants":[50],"of":[51,85],"this":[52,71,74],"architecture,":[53],"attention":[56,134],"mechanism":[57,135],"an":[59,104],"important":[60],"discovery.":[61],"Recently,":[62],"deep":[63,93],"learning":[64],"methods":[65],"have":[66],"achieved":[67],"state-of-the-art":[68],"results":[69],"problem.":[72],"In":[73,123],"paper,":[75],"we":[76,125],"present":[77],"model":[79,116],"that":[80],"generates":[81],"descriptions":[84],"images.":[87],"Our":[88],"approach":[89],"uses":[90],"pre-trained":[92],"neural":[94],"network":[95],"models":[96],"extract":[98],"visual":[99],"features":[100],"then":[102],"applies":[103],"LSTM":[105],"generate":[107],"captions.":[108],"We":[109],"use":[110],"BLEU":[111],"scores":[112],"evaluate":[114],"our":[115],"performance":[117],"on":[118],"Flickr8k":[119],"Flickr30k":[121],"dataset.":[122],"addition,":[124],"carried":[126],"out":[127],"comparison":[129],"between":[130],"approaches":[132],"without":[133],"attention-based":[137],"mechanism.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}