{"id":"https://openalex.org/W2508514999","doi":"https://doi.org/10.1007/s41095-016-0059-z","title":"LSTM-in-LSTM for generating long descriptions of images","display_name":"LSTM-in-LSTM for generating long descriptions of images","publication_year":2016,"publication_date":"2016-08-30","ids":{"openalex":"https://openalex.org/W2508514999","doi":"https://doi.org/10.1007/s41095-016-0059-z","mag":"2508514999"},"language":"en","primary_location":{"id":"doi:10.1007/s41095-016-0059-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41095-016-0059-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41095-016-0059-z.pdf","source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s41095-016-0059-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102010684","display_name":"Jun Song","orcid":"https://orcid.org/0000-0003-0659-1158"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Song","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063062444","display_name":"Siliang Tang","orcid":"https://orcid.org/0000-0002-7356-9711"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siliang Tang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101485989","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-6142-9914"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036747535","display_name":"Zhongfei Zhang","orcid":"https://orcid.org/0000-0001-5098-2506"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongfei Mark Zhang","raw_affiliation_strings":["Department of Computer Science, Watson School of Engineering and Applied Sciences, Binghamton University, Binghamton, NY, USA","Department of Computer Science, Watson School of Engineering and Applied Sciences, Binghamton University, Binghamton, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Watson School of Engineering and Applied Sciences, Binghamton University, Binghamton, NY, USA","institution_ids":["https://openalex.org/I123946342"]},{"raw_affiliation_string":"Department of Computer Science, Watson School of Engineering and Applied Sciences, Binghamton University, Binghamton, USA","institution_ids":["https://openalex.org/I123946342"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102010684"],"corresponding_institution_ids":["https://openalex.org/I168879160"],"apc_list":null,"apc_paid":null,"fwci":1.5204,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88350298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"2","issue":"4","first_page":"379","last_page":"388"},"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":0.9980999827384949,"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":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.8486705422401428},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.749820351600647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6632803082466125},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6432080268859863},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6405497789382935},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4854014813899994},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4798435866832733},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3975854516029358},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3676806092262268},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06974959373474121}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486705422401428},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.749820351600647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6632803082466125},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6432080268859863},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6405497789382935},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4854014813899994},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4798435866832733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3975854516029358},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3676806092262268},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06974959373474121},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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:10.1007/s41095-016-0059-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41095-016-0059-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41095-016-0059-z.pdf","source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s41095-016-0059-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41095-016-0059-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41095-016-0059-z.pdf","source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G114879407","display_name":null,"funder_award_id":"CCF-1017828","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2335687438","display_name":null,"funder_award_id":"2012CB316400","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4040737285","display_name":null,"funder_award_id":"61472353","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4370624215","display_name":"DC:Small: Collaborative Research: Data Intensive Computing for General Relational Data Learning","funder_award_id":"1017828","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5198779992","display_name":null,"funder_award_id":"2012CB31640","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5853313636","display_name":null,"funder_award_id":"Knowledge","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7608752429","display_name":null,"funder_award_id":"Talent","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8017731688","display_name":null,"funder_award_id":"2012CB316400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8240535094","display_name":null,"funder_award_id":"61572431","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327609","display_name":"China Knowledge Centre for Engineering Sciences and Technology","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2508514999.pdf","grobid_xml":"https://content.openalex.org/works/W2508514999.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W55204438","https://openalex.org/W68733909","https://openalex.org/W92662927","https://openalex.org/W100623710","https://openalex.org/W1502957213","https://openalex.org/W1514535095","https://openalex.org/W1593271688","https://openalex.org/W1686810756","https://openalex.org/W1687846465","https://openalex.org/W1785460851","https://openalex.org/W1810943226","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/W2094061585","https://openalex.org/W2101105183","https://openalex.org/W2102605133","https://openalex.org/W2109586012","https://openalex.org/W2112912048","https://openalex.org/W2121863487","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2142920810","https://openalex.org/W2143449221","https://openalex.org/W2149172860","https://openalex.org/W2149557440","https://openalex.org/W2179352600","https://openalex.org/W2185175083","https://openalex.org/W2526468814","https://openalex.org/W2607662938","https://openalex.org/W2618530766","https://openalex.org/W2771472444","https://openalex.org/W2949888546","https://openalex.org/W2950178297","https://openalex.org/W2951548327","https://openalex.org/W2962706528","https://openalex.org/W3098722327","https://openalex.org/W3122775348","https://openalex.org/W4206070039","https://openalex.org/W4214717370","https://openalex.org/W4234552385","https://openalex.org/W4236965008","https://openalex.org/W4301409532","https://openalex.org/W6603036350","https://openalex.org/W6605520847","https://openalex.org/W6743198006"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W4230315250"],"abstract_inverted_index":{"In":[0,15],"this":[1],"paper,":[2],"we":[3,17],"propose":[4],"an":[5,19,28,32],"approach":[6],"for":[7],"generating":[8],"rich":[9,133],"fine-grained":[10,109,134],"textual":[11],"descriptions":[12,135],"of":[13,27,70,78,108,136,141],"images.":[14],"particular,":[16],"use":[18],"LSTM-in-LSTM":[20],"(long":[21],"short-term":[22],"memory)":[23],"architecture,":[24],"which":[25],"consists":[26],"inner":[29,36,114],"LSTM":[30,37,56],"and":[31,65,72,104,148],"outer":[33,55,102],"LSTM.":[34],"The":[35],"effectively":[38],"encodes":[39],"the":[40,49,54,59,68,93,101,113],"long-range":[41],"implicit":[42],"contextual":[43],"interaction":[44],"between":[45,63],"visual":[46,51,110],"cues":[47,111],"(i.e.,":[48,67],"spatiallyconcurrent":[50],"objects),":[52],"while":[53],"generally":[57],"captures":[58],"explicit":[60],"multi-modal":[61],"relationship":[62],"sentences":[64,71],"images":[66,138],"correspondence":[69],"images).":[73],"This":[74],"architecture":[75],"is":[76],"capable":[77],"producing":[79],"a":[80,97,105],"long":[81,132],"description":[82],"by":[83],"predicting":[84],"one":[85],"word":[86],"at":[87],"every":[88],"time":[89],"step":[90],"conditioned":[91],"on":[92,121],"previously":[94],"generated":[95],"word,":[96],"hidden":[98],"vector":[99,107],"(via":[100,112],"LSTM),":[103],"context":[106],"LSTM).":[115],"Our":[116],"model":[117],"outperforms":[118],"state-of-theart":[119],"methods":[120],"several":[122],"benchmark":[123],"datasets":[124],"(Flickr8k,":[125],"Flickr30k,":[126],"MSCOCO)":[127],"when":[128],"used":[129],"to":[130],"generate":[131],"given":[137],"in":[139],"terms":[140],"four":[142],"different":[143],"metrics":[144],"(BLEU,":[145],"CIDEr,":[146],"ROUGE-L,":[147],"METEOR).":[149]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}