{"id":"https://openalex.org/W2752063835","doi":"https://doi.org/10.1109/icme.2017.8019525","title":"Keyword-driven image captioning via Context-dependent Bilateral LSTM","display_name":"Keyword-driven image captioning via Context-dependent Bilateral LSTM","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2752063835","doi":"https://doi.org/10.1109/icme.2017.8019525","mag":"2752063835"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2017.8019525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100356742","display_name":"Xiaodan Zhang","orcid":"https://orcid.org/0000-0001-7002-5447"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Xiaodan Zhang","raw_affiliation_strings":["City University of Hong Kong","University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056103024","display_name":"Shengfeng He","orcid":"https://orcid.org/0000-0002-3802-4644"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengfeng He","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055504013","display_name":"Xinhang Song","orcid":"https://orcid.org/0000-0002-0895-1076"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhang Song","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041227759","display_name":"Pengxu Wei","orcid":"https://orcid.org/0000-0002-2190-0767"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengxu Wei","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085719285","display_name":"Shuqiang Jiang","orcid":"https://orcid.org/0000-0002-1596-4326"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqiang Jiang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015317495","display_name":"Qixiang Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixiang Ye","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110088325","display_name":"Jianbin Jiao","orcid":"https://orcid.org/0000-0003-0454-3929"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbin Jiao","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006197413","display_name":"Rynson W. H. Lau","orcid":"https://orcid.org/0000-0002-8957-8129"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rynson W. H. Lau","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"781","last_page":"786"},"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":0.9966999888420105,"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/T11439","display_name":"Video Analysis and Summarization","score":0.984499990940094,"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":0.9493699669837952},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8659586906433105},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7246575355529785},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6823858618736267},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6736396551132202},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6697505116462708},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5914439558982849},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5813037753105164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5686822533607483},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5425662398338318},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.518694281578064},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5030991435050964},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3740256428718567},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07980212569236755}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9493699669837952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8659586906433105},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7246575355529785},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6823858618736267},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6736396551132202},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6697505116462708},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5914439558982849},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5813037753105164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5686822533607483},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5425662398338318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.518694281578064},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5030991435050964},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3740256428718567},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07980212569236755},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2017.8019525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-9500","is_oa":false,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/8497","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/ICME.2017.8019525","raw_type":"Conference Proceeding Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W92662927","https://openalex.org/W168564468","https://openalex.org/W639708223","https://openalex.org/W753012316","https://openalex.org/W1514535095","https://openalex.org/W1521626219","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2101105183","https://openalex.org/W2128856065","https://openalex.org/W2133512280","https://openalex.org/W2144715671","https://openalex.org/W2154652894","https://openalex.org/W2169818249","https://openalex.org/W2176091656","https://openalex.org/W2220981600","https://openalex.org/W2277195237","https://openalex.org/W2296385829","https://openalex.org/W2302086703","https://openalex.org/W2613718673","https://openalex.org/W2962706528","https://openalex.org/W2963758027","https://openalex.org/W6603785906","https://openalex.org/W6606906144","https://openalex.org/W6620707391","https://openalex.org/W6622239757","https://openalex.org/W6630875275","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6639694449","https://openalex.org/W6681516684","https://openalex.org/W6682631176","https://openalex.org/W6898505805"],"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/W2330246314","https://openalex.org/W3217195652"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"has":[2],"recently":[3],"received":[4],"much":[5],"attention.":[6],"Existing":[7],"approaches,":[8],"however,":[9],"are":[10],"limited":[11],"to":[12,24,63,93],"describing":[13],"images":[14],"with":[15,28,45,69,109,115,147],"simple":[16],"contextual":[17,32],"information,":[18],"which":[19],"typically":[20],"generate":[21,59],"one":[22],"sentence":[23,97],"describe":[25],"each":[26],"image":[27],"only":[29,134],"a":[30,42,46,84,95,110,116],"single":[31],"emphasis.":[33],"In":[34],"this":[35,39],"paper,":[36],"we":[37],"address":[38],"limitation":[40],"from":[41],"user":[43],"perspective":[44],"novel":[47],"approach.":[48],"Given":[49],"some":[50],"keywords":[51],"as":[52],"additional":[53],"inputs,":[54],"the":[55,64,76,100,124,130,137],"proposed":[56,131],"method":[57,80,139],"would":[58],"various":[60,148],"descriptions":[61,68],"according":[62],"provided":[65],"guidance.":[66],"Hence,":[67],"different":[70],"focuses":[71],"can":[72],"be":[73],"generated":[74],"for":[75],"same":[77],"image.":[78],"Our":[79],"is":[81,106],"based":[82],"on":[83,123],"new":[85],"Context-dependent":[86],"Bilateral":[87],"Long":[88],"Short-Term":[89],"Memory":[90],"(CDB-LSTM)":[91],"model":[92],"predict":[94],"keyword-driven":[96],"by":[98],"considering":[99],"word":[101,104],"dependence.":[102],"The":[103],"dependence":[105],"explored":[107],"externally":[108],"bilateral":[111],"pipeline,":[112],"and":[113,118,145],"internally":[114],"unified":[117],"joint":[119],"training":[120],"process.":[121],"Experiments":[122],"MS":[125],"COCO":[126],"dataset":[127],"demonstrate":[128],"that":[129],"approach":[132],"not":[133],"significantly":[135],"outperforms":[136],"baseline":[138],"but":[140],"also":[141],"shows":[142],"good":[143],"adaptation":[144],"consistency":[146],"keywords.":[149]},"counts_by_year":[{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}