{"id":"https://openalex.org/W2618127004","doi":"https://doi.org/10.1145/3078971.3079000","title":"Generating Video Descriptions with Topic Guidance","display_name":"Generating Video Descriptions with Topic Guidance","publication_year":2017,"publication_date":"2017-05-25","ids":{"openalex":"https://openalex.org/W2618127004","doi":"https://doi.org/10.1145/3078971.3079000","mag":"2618127004"},"language":"en","primary_location":{"id":"doi:10.1145/3078971.3079000","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3078971.3079000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","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/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":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743860","display_name":"Jia Chen","orcid":"https://orcid.org/0000-0003-2628-8471"},"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":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","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":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1144,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.89005687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5","last_page":"13"},"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":0.9991999864578247,"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":0.9954000115394592,"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":0.9645383358001709},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8666965961456299},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6164265275001526},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5686516165733337},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49583038687705994},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4848960041999817},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4700799286365509},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4649440348148346},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4514060914516449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4490882456302643},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4465479850769043},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39492908120155334},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18424376845359802}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9645383358001709},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8666965961456299},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6164265275001526},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5686516165733337},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49583038687705994},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4848960041999817},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4700799286365509},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4649440348148346},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4514060914516449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4490882456302643},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4465479850769043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39492908120155334},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18424376845359802},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3078971.3079000","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3078971.3079000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8600000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1821462560","https://openalex.org/W1828348983","https://openalex.org/W1880262756","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W1964442016","https://openalex.org/W1966385142","https://openalex.org/W1995820507","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2111078031","https://openalex.org/W2120190345","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2136036867","https://openalex.org/W2139501017","https://openalex.org/W2148154194","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2273041409","https://openalex.org/W2274287116","https://openalex.org/W2411037331","https://openalex.org/W2425121537","https://openalex.org/W2523993696","https://openalex.org/W2527349934","https://openalex.org/W2531044305","https://openalex.org/W2558834163","https://openalex.org/W2952881492","https://openalex.org/W2953022248","https://openalex.org/W2964018924","https://openalex.org/W2964241990","https://openalex.org/W6638523607","https://openalex.org/W6638549007"],"related_works":["https://openalex.org/W2547835662","https://openalex.org/W3185852197","https://openalex.org/W4200486724","https://openalex.org/W1483367581","https://openalex.org/W2783312365","https://openalex.org/W142374489","https://openalex.org/W4307348937","https://openalex.org/W2952674961","https://openalex.org/W4321080401","https://openalex.org/W2918969764"],"abstract_inverted_index":{"Generating":[0],"video":[1,7,126,152,210,231],"descriptions":[2,69],"in":[3,26,50,72,95,150,188,227],"natural":[4],"language":[5,200,233],"(a.k.a.":[6],"captioning)":[8],"is":[9],"a":[10,32,59,96,115,159],"more":[11,22],"challenging":[12],"task":[13],"than":[14,24,119],"image":[15],"captioning":[16],"as":[17,38,135,173,195],"the":[18,51,73,89,120,131,139,141,147,151,154,171,181,186,189,207,215,224,228],"videos":[19,30,71],"are":[20],"intrinsically":[21],"complicated":[23],"images":[25],"two":[27],"aspects.":[28],"First,":[29],"cover":[31],"broader":[33],"range":[34],"of":[35,161,198,217],"topics,":[36,83],"such":[37],"news,":[39],"music,":[40],"sports":[41],"and":[42,183],"so":[43],"on.":[44],"Second,":[45],"multiple":[46],"topics":[47,94,113,172,192],"could":[48],"coexist":[49],"same":[52],"video.":[53],"In":[54,79],"this":[55],"paper,":[56],"we":[57,91,129],"propose":[58,158],"novel":[60],"caption":[61,162,211],"model,":[62,144,220],"topic-guided":[63,219],"model":[64,134],"(TGM),":[65],"to":[66,81,137,164,176,180,193,232],"generate":[67,177],"topic-oriented":[68],"for":[70,124],"wild":[74],"via":[75],"exploiting":[76],"topic":[77,106,117,127,132,142,166,182],"information.":[78],"addition":[80],"predefined":[82,121],"i.e.,":[84],"category":[85],"tags":[86],"crawled":[87],"from":[88],"web,":[90],"also":[92],"mine":[93],"data-driven":[97,112],"way":[98],"based":[99],"on":[100,206],"training":[101],"captions":[102],"by":[103,145],"an":[104,196],"unsupervised":[105],"mining":[107,133],"model.":[108],"We":[109,157],"show":[110],"that":[111],"reflect":[114],"better":[116],"schema":[118],"topics.":[122],"As":[123],"testing":[125],"prediction,":[128],"treat":[130],"teacher":[136],"train":[138],"student,":[140],"prediction":[143],"utilizing":[146],"full":[148],"multi-modalities":[149],"especially":[153],"speech":[155],"modality.":[156],"series":[160],"models":[163],"exploit":[165],"guidance,":[167],"including":[168],"implicitly":[169],"using":[170],"input":[174],"features":[175],"words":[178],"related":[179],"explicitly":[184],"modifying":[185],"weights":[187],"decoder":[190],"with":[191],"function":[194],"ensemble":[197],"topic-aware":[199],"decoders.":[201],"Our":[202],"comprehensive":[203],"experimental":[204],"results":[205],"current":[208],"largest":[209],"dataset":[212],"MSR-VTT":[213],"prove":[214],"effectiveness":[216],"our":[218],"which":[221],"significantly":[222],"surpasses":[223],"winning":[225],"performance":[226],"2016":[229],"MSR":[230],"challenge.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}