{"id":"https://openalex.org/W2887712318","doi":"https://doi.org/10.1109/tip.2018.2855422","title":"Video Captioning by Adversarial LSTM","display_name":"Video Captioning by Adversarial LSTM","publication_year":2018,"publication_date":"2018-07-12","ids":{"openalex":"https://openalex.org/W2887712318","doi":"https://doi.org/10.1109/tip.2018.2855422","mag":"2887712318","pmid":"https://pubmed.ncbi.nlm.nih.gov/30010568"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2018.2855422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2855422","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5070-4511","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066557235","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0002-3836-4163"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003219284","display_name":"Jiangbo Ai","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangbo Ai","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Bin","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037486611","display_name":"Alan Hanjali\u0107","orcid":"https://orcid.org/0000-0002-5771-2549"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alan Hanjalic","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068950059","display_name":"Yanli Ji","orcid":"https://orcid.org/0000-0001-9122-6141"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanli Ji","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-9122-6141","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.8606,"has_fulltext":false,"cited_by_count":219,"citation_normalized_percentile":{"value":0.99364375,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"27","issue":"11","first_page":"5600","last_page":"5611"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9991000294685364,"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":0.9950000047683716,"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":0.9410727620124817},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7828148603439331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7123304605484009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6257463693618774},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.549592912197113},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4060235917568207},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3135837912559509}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9410727620124817},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7828148603439331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7123304605484009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6257463693618774},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.549592912197113},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4060235917568207},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3135837912559509}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tip.2018.2855422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2855422","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:30010568","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30010568","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/131424","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/131424","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:tudelft.nl:uuid:2e269108-ede2-4d99-9116-e80dd92cbb6f","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:2e269108-ede2-4d99-9116-e80dd92cbb6f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1816382614","display_name":"\u534f\u540c\u89c6\u89c9\u8bed\u4e49\u7406\u89e3\u548c\u793e\u4f1a\u5a92\u4f53\u5206\u6790\u7684\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61572108","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3623292902","display_name":null,"funder_award_id":"61632007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8622808977","display_name":null,"funder_award_id":"B17008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8978917354","display_name":null,"funder_award_id":"B17008","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1572567476","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1686810756","https://openalex.org/W1714639292","https://openalex.org/W1775434803","https://openalex.org/W1832693441","https://openalex.org/W1889081078","https://openalex.org/W1893116441","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W2053831280","https://openalex.org/W2064675550","https://openalex.org/W2078238240","https://openalex.org/W2080672747","https://openalex.org/W2099471712","https://openalex.org/W2101105183","https://openalex.org/W2101801316","https://openalex.org/W2119717200","https://openalex.org/W2127615881","https://openalex.org/W2130942839","https://openalex.org/W2131342762","https://openalex.org/W2133459682","https://openalex.org/W2136036867","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2150355110","https://openalex.org/W2152984213","https://openalex.org/W2154652894","https://openalex.org/W2158899491","https://openalex.org/W2164290393","https://openalex.org/W2174424190","https://openalex.org/W2210838531","https://openalex.org/W2250539671","https://openalex.org/W2265846598","https://openalex.org/W2282231212","https://openalex.org/W2302086703","https://openalex.org/W2425121537","https://openalex.org/W2476099471","https://openalex.org/W2513281263","https://openalex.org/W2519536754","https://openalex.org/W2523469089","https://openalex.org/W2548228487","https://openalex.org/W2556388456","https://openalex.org/W2558834163","https://openalex.org/W2581637843","https://openalex.org/W2593190442","https://openalex.org/W2597985671","https://openalex.org/W2611926148","https://openalex.org/W2622385665","https://openalex.org/W2625940279","https://openalex.org/W2665436006","https://openalex.org/W2739103128","https://openalex.org/W2739107216","https://openalex.org/W2752930373","https://openalex.org/W2803620531","https://openalex.org/W2949541494","https://openalex.org/W2949828251","https://openalex.org/W2950560720","https://openalex.org/W2951520714","https://openalex.org/W2952165242","https://openalex.org/W2952230511","https://openalex.org/W2962968835","https://openalex.org/W2963223306","https://openalex.org/W2963373786","https://openalex.org/W2963576560","https://openalex.org/W2964083091","https://openalex.org/W2964137974","https://openalex.org/W2964222573","https://openalex.org/W2964241990","https://openalex.org/W2964268978","https://openalex.org/W4320013936","https://openalex.org/W6630875275","https://openalex.org/W6664008549","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6683738474","https://openalex.org/W6684090549","https://openalex.org/W6693505360","https://openalex.org/W6718379498","https://openalex.org/W6727063399","https://openalex.org/W6746707065","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"In":[0],"this":[1,21],"paper,":[2],"we":[3,24,61,127,140,172],"propose":[4,141],"a":[5,63,78,89,92,142],"novel":[6,143],"approach":[7],"to":[8,40,119,164,175],"video":[9,33,46,131,149,158],"captioning":[10,34,132,150],"based":[11],"on":[12,181],"adversarial":[13],"learning":[14],"and":[15,91,111,152,157],"Long-Short":[16],"Term":[17],"Memory":[18],"(LSTM).":[19],"With":[20],"solution":[22],"concept":[23,133],"aim":[25],"at":[26],"compensating":[27],"for":[28,147,170],"the":[29,85,96,99,109,117,124,138,148,155,178],"deficiencies":[30],"of":[31,45,74,88,98],"LSTM-based":[32],"methods":[35,180],"that":[36,52],"generally":[37],"show":[38,173],"potential":[39],"effectively":[41],"handle":[42],"temporal":[43],"nature":[44],"data":[47],"when":[48],"generating":[49],"captions,":[50],"but":[51],"also":[53],"typically":[54],"suffer":[55],"from":[56],"exponential":[57],"error":[58],"accumulation.":[59],"Specifically,":[60],"adopt":[62],"standard":[64,182],"Generative":[65],"Adversarial":[66],"Network":[67],"(GAN)":[68],"architecture,":[69,169],"characterized":[70],"by":[71],"an":[72,106,129],"interplay":[73],"two":[75],"competing":[76],"processes:":[77],"\"generator\",":[79],"which":[80,94,171],"generates":[81],"textual":[82],"sentences":[83,156],"given":[84],"visual":[86],"content":[87],"video,":[90],"\"discriminator\"":[93],"controls":[95],"accuracy":[97],"generated":[100],"sentences.":[101],"The":[102],"discriminator":[103],"acts":[104],"as":[105,160],"\"adversary\"":[107],"towards":[108],"generator":[110,118,125],"with":[112],"its":[113],"controlling":[114],"mechanism":[115],"helps":[116],"become":[120],"more":[121],"accurate.":[122],"For":[123,137],"module,":[126],"take":[128],"existing":[130,179],"using":[134],"LSTM":[135],"network.":[136],"discriminator,":[139],"realization":[144],"specifically":[145],"tuned":[146],"problem":[151],"taking":[153],"both":[154],"features":[159],"input.":[161],"This":[162],"leads":[163],"our":[165],"proposed":[166],"LSTM-GAN":[167],"system":[168],"experimentally":[174],"significantly":[176],"outperform":[177],"public":[183],"datasets.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":38},{"year":2021,"cited_by_count":35},{"year":2020,"cited_by_count":46},{"year":2019,"cited_by_count":34},{"year":2018,"cited_by_count":15}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}