{"id":"https://openalex.org/W2913822893","doi":"https://doi.org/10.1109/tmm.2019.2896515","title":"Generating Video Descriptions With Latent Topic Guidance","display_name":"Generating Video Descriptions With Latent Topic Guidance","publication_year":2019,"publication_date":"2019-01-30","ids":{"openalex":"https://openalex.org/W2913822893","doi":"https://doi.org/10.1109/tmm.2019.2896515","mag":"2913822893"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2896515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2896515","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},"type":"article","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/A5101776086","display_name":"Shizhe Chen","orcid":"https://orcid.org/0000-0002-7313-9703"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shizhe Chen","raw_affiliation_strings":["School of Information, Renmin University of China, Beijing, China","School of Information, Renmin University of China Beijing, China#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-7313-9703","affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Information, Renmin University of China Beijing, China#TAB#","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["School of Information, Renmin University of China, Beijing, China","School of Information, Renmin University of China Beijing, China#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-6486-6020","affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"School of Information, Renmin University of China Beijing, China#TAB#","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416039","display_name":"Jia Chen","orcid":"https://orcid.org/0009-0005-0957-1744"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Chen","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Tech. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Tech. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103099928","display_name":"Alexander G. Hauptmann","orcid":"https://orcid.org/0000-0003-2123-0684"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander G. Hauptmann","raw_affiliation_strings":["Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4813,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.91553142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"21","issue":"9","first_page":"2407","last_page":"2418"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9993000030517578,"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":0.9976000189781189,"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":0.971493661403656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8784040808677673},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5931980609893799},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5352751612663269},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5001261234283447},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4793856143951416},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.47703665494918823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4442167580127716},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42889857292175293},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4088316857814789},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3960120677947998},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38956061005592346},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.096133291721344}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.971493661403656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8784040808677673},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5931980609893799},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5352751612663269},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5001261234283447},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4793856143951416},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.47703665494918823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4442167580127716},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42889857292175293},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4088316857814789},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3960120677947998},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38956061005592346},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.096133291721344},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2019.2896515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2896515","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G3625693645","display_name":null,"funder_award_id":"61772535","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1821462560","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W1964442016","https://openalex.org/W1966385142","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2120190345","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2134797427","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2148154194","https://openalex.org/W2154652894","https://openalex.org/W2156387975","https://openalex.org/W2161000554","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2411037331","https://openalex.org/W2425121537","https://openalex.org/W2474516730","https://openalex.org/W2506483933","https://openalex.org/W2507365558","https://openalex.org/W2527349934","https://openalex.org/W2554906389","https://openalex.org/W2557264465","https://openalex.org/W2558834163","https://openalex.org/W2575629043","https://openalex.org/W2584992898","https://openalex.org/W2596720518","https://openalex.org/W2607119937","https://openalex.org/W2613964630","https://openalex.org/W2618127004","https://openalex.org/W2618530766","https://openalex.org/W2621571501","https://openalex.org/W2732026016","https://openalex.org/W2752172973","https://openalex.org/W2752191396","https://openalex.org/W2963084599","https://openalex.org/W2963150697","https://openalex.org/W2963177403","https://openalex.org/W2963576560","https://openalex.org/W2963843052","https://openalex.org/W2964049455","https://openalex.org/W2964121744","https://openalex.org/W2964241990","https://openalex.org/W2964308564","https://openalex.org/W2964350391","https://openalex.org/W3098682680","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6679434410","https://openalex.org/W6679909955","https://openalex.org/W6680145277","https://openalex.org/W6682631176","https://openalex.org/W6682889407","https://openalex.org/W6694260854","https://openalex.org/W6725318829","https://openalex.org/W6729046916","https://openalex.org/W6731907337","https://openalex.org/W6743384090"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Automatic":[0],"video":[1,5,14,24,30,43,66,98,107,155,273,293],"description":[2],"generation":[3,119,126,174],"(a.k.a":[4],"captioning)":[6],"is":[7,140,186,213,227],"one":[8],"of":[9,20,42,52,112,135,289],"the":[10,17,29,38,65,103,132,136,163,172,178,190,198,203,247,253,287,290],"ultimate":[11],"goals":[12],"for":[13,181],"understanding.":[15],"Despite":[16],"wide":[18],"range":[19,51],"applications":[21],"such":[22],"as":[23],"indexing":[25],"and":[26,40,60,77,120,157,160,216,245,264,271,284],"retrieval":[27],"etc.,":[28],"captioning":[31,99,294],"task":[32,127],"remains":[33],"quite":[34],"challenging":[35],"due":[36],"to":[37,63,101,129,166,187,201,206,228,231,251,267],"complexity":[39,192],"diversity":[41],"content.":[44],"First,":[45],"open-domain":[46],"videos":[47,69],"cover":[48],"a":[49,95,167,221,239],"broad":[50],"topics,":[53,194,235],"which":[54,296],"results":[55],"in":[56,87,106,149],"highly":[57],"variable":[58],"vocabularies":[59],"expression":[61],"styles":[62],"describe":[64],"contents.":[67],"Second,":[68],"naturally":[70],"contain":[71],"multiple":[72],"modalities":[73,85,233],"including":[74],"image,":[75],"motion,":[76],"acoustic":[78],"media.":[79],"The":[80,124,184,211,225,256],"information":[81],"provided":[82],"by":[83,234],"different":[84,88],"differs":[86],"conditions.":[89],"In":[90,171],"this":[91],"paper,":[92],"we":[93,145,176,196,237],"propose":[94,197,238],"novel":[96],"topic-guided":[97,121,173,241,292],"model":[100,110],"address":[102],"above-mentioned":[104],"challenges":[105],"captioning.":[108],"Our":[109,275],"consists":[111],"two":[113,182,257,279],"joint":[114],"tasks,":[115],"namely,":[116],"latent":[117,133,204],"topic":[118,125,134,143,164,168,179,248],"caption":[122],"generation.":[123],"aims":[128],"automatically":[130],"predict":[131],"video.":[137],"Since":[138],"there":[139],"no":[141],"groundtruth":[142],"information,":[144],"mine":[146],"multimodal":[147,242],"topics":[148,205],"an":[150],"unsupervised":[151],"fashion":[152],"based":[153],"on":[154,278,300],"contents":[156],"annotated":[158],"captions,":[159],"then":[161],"distill":[162],"distribution":[165],"prediction":[169],"model.":[170],"task,":[175],"employ":[177],"guidance":[180],"purposes.":[183],"first":[185],"narrow":[188],"down":[189],"language":[191,209],"across":[193],"where":[195,236],"topic-aware":[199],"decoder":[200,212],"leverage":[202],"induce":[207],"topic-related":[208],"models.":[210],"also":[214],"generic":[215],"can":[217],"be":[218],"integrated":[219],"with":[220,261],"temporal":[222],"attention":[223,254],"mechanism.":[224],"second":[226],"dynamically":[229],"attend":[230],"important":[232],"flexible":[240],"ensemble":[243],"framework":[244],"use":[246],"gating":[249],"network":[250],"determine":[252],"weights.":[255],"tasks":[258],"are":[259],"correlated":[260],"each":[262],"other,":[263],"they":[265],"collaborate":[266],"generate":[268],"more":[269],"detailed":[270],"accurate":[272],"captions.":[274],"extensive":[276],"experiments":[277],"public":[280],"benchmark":[281],"datasets":[282],"MSR-VTT":[283],"Youtube2Text":[285],"demonstrate":[286],"effectiveness":[288],"proposed":[291],"system,":[295],"achieves":[297],"state-of-the-art":[298],"performance":[299],"both":[301],"datasets.":[302]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}