{"id":"https://openalex.org/W2523993696","doi":"https://doi.org/10.1145/2964284.2984066","title":"Multimodal Video Description","display_name":"Multimodal Video Description","publication_year":2016,"publication_date":"2016-09-29","ids":{"openalex":"https://openalex.org/W2523993696","doi":"https://doi.org/10.1145/2964284.2984066","mag":"2523993696"},"language":"en","primary_location":{"id":"doi:10.1145/2964284.2984066","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2984066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-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/A5001707003","display_name":"Vasili Ramanishka","orcid":null},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vasili Ramanishka","raw_affiliation_strings":["University of Massachusetts Lowell, Lowell, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell, Lowell, MA, USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101751934","display_name":"Abir Das","orcid":"https://orcid.org/0000-0002-2327-1618"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abir Das","raw_affiliation_strings":["University of Massachusetts Lowell, Lowell, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell, Lowell, MA, USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027383005","display_name":"Dong Huk Park","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Huk Park","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025689655","display_name":"Subhashini Venugopalan","orcid":"https://orcid.org/0000-0003-3729-8456"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subhashini Venugopalan","raw_affiliation_strings":["University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020758501","display_name":"Lisa Anne Hendricks","orcid":"https://orcid.org/0000-0001-9340-5143"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lisa Anne Hendricks","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024481540","display_name":"Marcus Rohrbach","orcid":"https://orcid.org/0000-0001-5908-7751"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcus Rohrbach","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075906727","display_name":"Kate Saenko","orcid":"https://orcid.org/0000-0002-7564-7218"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kate Saenko","raw_affiliation_strings":["University of Massachusetts Lowell, Lowell, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell, Lowell, MA, USA","institution_ids":["https://openalex.org/I133738476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5001707003"],"corresponding_institution_ids":["https://openalex.org/I133738476"],"apc_list":null,"apc_paid":null,"fwci":12.1914,"has_fulltext":false,"cited_by_count":145,"citation_normalized_percentile":{"value":0.99056841,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1092","last_page":"1096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9970999956130981,"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":0.9944000244140625,"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/computer-science","display_name":"Computer science","score":0.8478526473045349},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6316659450531006},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6205870509147644},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6039363741874695},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6022856831550598},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5853912234306335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5019116401672363},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4921185374259949},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46884405612945557},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3357648551464081},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32171928882598877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478526473045349},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6316659450531006},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6205870509147644},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6039363741874695},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6022856831550598},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5853912234306335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5019116401672363},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4921185374259949},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46884405612945557},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3357648551464081},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32171928882598877},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2964284.2984066","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2984066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W1522734439","https://openalex.org/W1687846465","https://openalex.org/W1893116441","https://openalex.org/W1897761818","https://openalex.org/W1956340063","https://openalex.org/W1987835821","https://openalex.org/W1995820507","https://openalex.org/W2016053056","https://openalex.org/W2064675550","https://openalex.org/W2066134726","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2133512280","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2152984213","https://openalex.org/W2154652894","https://openalex.org/W2160815625","https://openalex.org/W2162676242","https://openalex.org/W2184045248","https://openalex.org/W2187089797","https://openalex.org/W2192412620","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2271840356","https://openalex.org/W2321588627","https://openalex.org/W2425121537","https://openalex.org/W2559655401","https://openalex.org/W2949888546","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4283822356","https://openalex.org/W1950940422","https://openalex.org/W2129146436","https://openalex.org/W2032507829","https://openalex.org/W2147282173"],"abstract_inverted_index":{"Real-world":[0],"web":[1],"videos":[2,54,138],"often":[3],"contain":[4],"cues":[5],"to":[6,41,49,60,101,104,111,127],"supplement":[7],"visual":[8,43,67],"information":[9,44,68,80],"for":[10],"generating":[11],"natural":[12,137],"language":[13],"descriptions.":[14],"In":[15,28,58],"this":[16],"paper":[17],"we":[18],"propose":[19],"a":[20,46],"sequence-to-sequence":[21],"model":[22,75,107],"which":[23,65],"explores":[24],"such":[25],"auxiliary":[26],"information.":[27],"particular,":[29],"audio":[30],"and":[31,108],"the":[32,35,42,56,71,86,98,120,129,133,141],"topic":[33],"of":[34,53,79,114,132],"video":[36,94,103],"are":[37,124],"used":[38],"in":[39,45,140],"addition":[40],"multimodal":[47,93],"framework":[48],"generate":[50],"coherent":[51],"descriptions":[52],"\"in":[55],"wild\".":[57],"contrast":[59],"current":[61],"encoder-decoder":[62],"based":[63,91],"models":[64],"exploit":[66],"only":[69],"during":[70],"encoding":[72],"stage,":[73],"our":[74,92],"fuses":[76],"multiple":[77,115],"sources":[78],"judiciously,":[81],"showing":[82],"improvement":[83],"over":[84],"using":[85],"different":[87],"modalities":[88],"separately.":[89],"We":[90],"description":[95],"network":[96],"on":[97,119,136],"state-of-the-art":[99],"sequence":[100,102],"text":[105],"(S2VT)":[106],"extended":[109],"it":[110],"take":[112],"advantage":[113],"modalities.":[116],"Extensive":[117],"experiments":[118],"challenging":[121],"MSR-VTT":[122],"dataset":[123],"carried":[125],"out":[126],"show":[128],"superior":[130],"performance":[131],"proposed":[134],"approach":[135],"found":[139],"web.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":34},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":18},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
