{"id":"https://openalex.org/W2808206191","doi":"https://doi.org/10.24963/ijcai.2018/110","title":"Image Cationing with Visual-Semantic LSTM","display_name":"Image Cationing with Visual-Semantic LSTM","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2808206191","doi":"https://doi.org/10.24963/ijcai.2018/110","mag":"2808206191"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/110","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/110","pdf_url":"https://www.ijcai.org/proceedings/2018/0110.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0110.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100419522","display_name":"Nannan Li","orcid":"https://orcid.org/0000-0002-1545-019X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nannan Li","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, P.R. China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006748765","display_name":"Zhenzhong Chen","orcid":"https://orcid.org/0000-0002-7882-1066"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenzhong Chen","raw_affiliation_strings":["School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, P.R. China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006748765"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":1.3813,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.86082548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"793","last_page":"799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9940999746322632,"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":0.8661359548568726},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8467689752578735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6536940336227417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6001585721969604},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5580708980560303},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49124640226364136},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.47721415758132935},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4556144177913666},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3429223895072937},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.062141239643096924}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8661359548568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467689752578735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6536940336227417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6001585721969604},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5580708980560303},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49124640226364136},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.47721415758132935},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4556144177913666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3429223895072937},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.062141239643096924},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/110","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/110","pdf_url":"https://www.ijcai.org/proceedings/2018/0110.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/110","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/110","pdf_url":"https://www.ijcai.org/proceedings/2018/0110.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G3263127771","display_name":null,"funder_award_id":"61471273","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5543094251","display_name":null,"funder_award_id":"61771348","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2808206191.pdf","grobid_xml":"https://content.openalex.org/works/W2808206191.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1811254738","https://openalex.org/W1836465849","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W2145315825","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2558834163","https://openalex.org/W2575842049","https://openalex.org/W2607151106","https://openalex.org/W2607768201","https://openalex.org/W2740118378","https://openalex.org/W2740747242","https://openalex.org/W2745461083","https://openalex.org/W2962935746","https://openalex.org/W2963084599","https://openalex.org/W2964018924","https://openalex.org/W2964168617","https://openalex.org/W4214717370"],"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/W2330246314","https://openalex.org/W3217195652"],"abstract_inverted_index":{"In":[0,55],"this":[1],"paper,":[2],"a":[3,27,57],"novel":[4],"image":[5],"captioning":[6],"approach":[7,93],"is":[8,61],"proposed":[9],"to":[10,31,63,73,96],"describe":[11],"the":[12,18,33,41,52,64,69,78,89,97],"content":[13],"of":[14,21,91],"images.":[15],"Inspired":[16],"by":[17],"visual":[19,42],"processing":[20],"our":[22,92],"cognitive":[23],"system,":[24],"we":[25],"propose":[26],"visual-semantic":[28],"LSTM":[29],"model":[30],"locate":[32],"attention":[34],"objects":[35],"with":[36],"their":[37],"low-level":[38],"features":[39,50],"in":[40,51,68,77],"cell,":[43],"and":[44,86],"then":[45],"successively":[46],"extract":[47],"high-level":[48],"semantic":[49,53],"cell.":[54],"addition,":[56],"state":[58],"perturbation":[59],"term":[60],"introduced":[62],"word":[65],"sampling":[66],"strategy":[67],"REINFORCE":[70],"based":[71],"method":[72],"explore":[74],"proper":[75],"vocabularies":[76],"training":[79],"process.":[80],"Experimental":[81],"results":[82],"on":[83],"MS":[84],"COCO":[85],"Flickr30K":[87],"validate":[88],"effectiveness":[90],"when":[94],"compared":[95],"state-of-the-art":[98],"methods.":[99]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
