{"id":"https://openalex.org/W2968320615","doi":"https://doi.org/10.1145/3342999.3343004","title":"Practice in Caption Generation with Keras","display_name":"Practice in Caption Generation with Keras","publication_year":2019,"publication_date":"2019-07-05","ids":{"openalex":"https://openalex.org/W2968320615","doi":"https://doi.org/10.1145/3342999.3343004","mag":"2968320615"},"language":"en","primary_location":{"id":"doi:10.1145/3342999.3343004","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342999.3343004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Deep Learning Technologies","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/A5100324886","display_name":"Rong Wang","orcid":"https://orcid.org/0000-0002-2519-0512"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Rong Wang","raw_affiliation_strings":["Hosei University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Hosei University, Tokyo, Japan","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076148615","display_name":"Toru Wakahara","orcid":"https://orcid.org/0000-0002-2091-3363"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Wakahara","raw_affiliation_strings":["Hosei University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Hosei University, Tokyo, Japan","institution_ids":["https://openalex.org/I204291657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100324886"],"corresponding_institution_ids":["https://openalex.org/I204291657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07702383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"15"},"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":0.9965999722480774,"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":0.9961000084877014,"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/benchmark","display_name":"Benchmark (surveying)","score":0.833184540271759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7875342965126038},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.7203261852264404},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6855104565620422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5830793380737305},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5203718543052673},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4484420716762543},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4253826141357422},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22875797748565674}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.833184540271759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875342965126038},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7203261852264404},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6855104565620422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5830793380737305},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5203718543052673},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4484420716762543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4253826141357422},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22875797748565674},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3342999.3343004","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342999.3343004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Deep Learning Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W1931639407","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2115595010","https://openalex.org/W2141399712","https://openalex.org/W2171361956","https://openalex.org/W2538374209","https://openalex.org/W2900953995","https://openalex.org/W2950178297","https://openalex.org/W2953022248","https://openalex.org/W2953106684","https://openalex.org/W2964253311"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2130974462","https://openalex.org/W2144453115","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W3088304681"],"abstract_inverted_index":{"Hard-attention":[0],"model":[1,13,90],"has":[2],"been":[3],"proposed":[4],"for":[5,9,46],"automatically":[6],"generating":[7],"captions":[8],"images.":[10],"Currently":[11],"this":[12,38,53],"is":[14,24,77,91],"implemented":[15],"in":[16,26],"many":[17],"ways.":[18],"For":[19],"instance,":[20],"its":[21],"original":[22,70],"implementation":[23],"written":[25,33],"Theano":[27],"and":[28,63,85],"most":[29],"other":[30,102],"implementations":[31],"are":[32,65],"using":[34],"Tensorflow":[35],"library.":[36],"In":[37],"paper,":[39],"we":[40],"use":[41],"Keras,":[42],"a":[43],"modular":[44],"framework":[45],"constructing":[47],"deep":[48],"neural":[49],"networks,":[50],"to":[51,79,94],"implement":[52],"model.":[54,72],"We":[55],"also":[56],"propose":[57],"two":[58,103],"attention":[59,71,83],"models,":[60,84],"called":[61],"Attention-L":[62],"Attention-C,":[64],"slightly":[66],"modified":[67],"from":[68],"the":[69,86,96],"The":[73],"benchmark":[74],"dataset":[75],"Flickr30":[76],"used":[78],"compare":[80],"these":[81],"three":[82],"results":[87],"demonstrate":[88],"Attention-C":[89],"more":[92],"likely":[93],"obtain":[95],"better":[97],"scores":[98],"than":[99],"that":[100],"of":[101],"models.":[104]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}