{"id":"https://openalex.org/W2751153269","doi":"https://doi.org/10.1109/icme.2017.8019408","title":"Image captioning with deep LSTM based on sequential residual","display_name":"Image captioning with deep LSTM based on sequential residual","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2751153269","doi":"https://doi.org/10.1109/icme.2017.8019408","mag":"2751153269"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2017.8019408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019408","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/A5101839579","display_name":"Kaisheng Xu","orcid":"https://orcid.org/0000-0002-7455-8352"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaisheng Xu","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, Shanghai, CN","Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, Shanghai, CN","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, CN","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","Key Laboratory of Embedded System and Service Computing, Tongji University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102827532","display_name":"Pengjie Tang","orcid":"https://orcid.org/0000-0001-7523-0175"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengjie Tang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","Key Laboratory of Embedded System and Service Computing, Tongji University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"361","last_page":"366"},"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":0.9926000237464905,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9205471277236938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8597887754440308},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7605985403060913},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.753216028213501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.662432074546814},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5970353484153748},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5558359622955322},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5335932970046997},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4684318006038666},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46723228693008423},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4587417542934418},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.453545480966568},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43366968631744385},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4085090160369873},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3758794069290161},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22619017958641052},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19562044739723206}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9205471277236938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597887754440308},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7605985403060913},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.753216028213501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.662432074546814},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5970353484153748},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5558359622955322},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5335932970046997},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4684318006038666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46723228693008423},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4587417542934418},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.453545480966568},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43366968631744385},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4085090160369873},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3758794069290161},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22619017958641052},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19562044739723206},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2017.8019408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019408","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W68733909","https://openalex.org/W1026270304","https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2171361956","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2296385829","https://openalex.org/W2345474290","https://openalex.org/W2397299141","https://openalex.org/W2950621961","https://openalex.org/W2962706528","https://openalex.org/W2962835968","https://openalex.org/W2963077256","https://openalex.org/W2964018924","https://openalex.org/W6600213771","https://openalex.org/W6626481562","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6639694449","https://openalex.org/W6674330103","https://openalex.org/W6678262379","https://openalex.org/W6685230081","https://openalex.org/W6704604629","https://openalex.org/W6712635486","https://openalex.org/W6898505805"],"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/W2790400419"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"is":[2,46,68,106],"a":[3,40,101],"fundamental":[4],"task":[5],"which":[6],"requires":[7],"semantic":[8],"understanding":[9],"of":[10,15,26,75],"images":[11],"and":[12,21,117,135],"the":[13,27,52,72,90,114,122,126],"ability":[14],"generating":[16],"description":[17],"sentences":[18],"with":[19,51,129],"proper":[20],"correct":[22],"structure.":[23],"In":[24],"consideration":[25],"problem":[28,92],"that":[29,121],"language":[30,66],"models":[31],"are":[32],"always":[33],"shallow":[34],"in":[35,48,86,97,131,137],"modern":[36],"image":[37],"caption":[38],"frameworks,":[39],"deep":[41,59],"residual":[42,73],"recurrent":[43],"neural":[44],"network":[45],"proposed":[47,107,123],"this":[49],"work":[50],"following":[53],"two":[54],"contributions.":[55],"First,":[56],"an":[57],"easy-to-train":[58],"stacked":[60],"Long":[61],"Short":[62],"Term":[63],"Memory":[64],"(LSTM)":[65],"model":[67,124],"designed":[69],"to":[70,82,88],"learn":[71],"function":[74],"output":[76],"distributions":[77],"by":[78,94],"adding":[79],"identity":[80],"mappings":[81],"multi-layer":[83],"LSTMs.":[84],"Second,":[85],"order":[87],"overcome":[89],"over-fitting":[91],"caused":[93],"larger-scale":[95],"parameters":[96],"deeper":[98],"LSTM":[99],"networks,":[100],"novel":[102],"temporal":[103],"Dropout":[104],"method":[105],"into":[108],"LSTM.":[109],"The":[110],"experimental":[111],"results":[112],"on":[113,133,139],"benchmark":[115],"MSCOCO":[116,134],"Flickr30K":[118],"datasets":[119],"demonstrate":[120],"achieves":[125],"state-of-the-art":[127],"performances":[128],"101.1":[130],"CIDEr":[132],"22.9":[136],"B-4":[138],"Flickr30K,":[140],"respectively.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}