{"id":"https://openalex.org/W2766159440","doi":"https://doi.org/10.1145/3123266.3127904","title":"Multirate Multimodal Video Captioning","display_name":"Multirate Multimodal Video Captioning","publication_year":2017,"publication_date":"2017-10-20","ids":{"openalex":"https://openalex.org/W2766159440","doi":"https://doi.org/10.1145/3123266.3127904","mag":"2766159440"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3127904","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3127904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","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/A5070359048","display_name":"Ziwei Yang","orcid":"https://orcid.org/0000-0001-9846-840X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziwei Yang","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067796638","display_name":"Youjiang Xu","orcid":"https://orcid.org/0000-0002-2438-3136"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youjiang Xu","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071211512","display_name":"Hui\u2010Yun Wang","orcid":"https://orcid.org/0000-0001-6728-4376"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyun Wang","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Wang","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031819155","display_name":"Yahong Han","orcid":"https://orcid.org/0000-0003-2768-1398"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahong Han","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1877","last_page":"1882"},"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":0.9970999956130981,"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/T11439","display_name":"Video Analysis and Summarization","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":0.9230331182479858},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8657734394073486},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5559972524642944},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5464611649513245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5440272092819214},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5321323871612549},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.519982635974884},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5034274458885193},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4813419282436371},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.46868306398391724},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.45296502113342285},{"id":"https://openalex.org/keywords/videoconferencing","display_name":"Videoconferencing","score":0.41269588470458984},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.3088819980621338},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.29721295833587646},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12623968720436096}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9230331182479858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8657734394073486},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5559972524642944},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5464611649513245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5440272092819214},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5321323871612549},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.519982635974884},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5034274458885193},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4813419282436371},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.46868306398391724},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.45296502113342285},{"id":"https://openalex.org/C22561748","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videoconferencing","level":2,"score":0.41269588470458984},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3088819980621338},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.29721295833587646},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12623968720436096},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123266.3127904","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3127904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G5877558009","display_name":null,"funder_award_id":"U1509206, 61472276","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1536680647","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W2080672747","https://openalex.org/W2101105183","https://openalex.org/W2139501017","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2410323755","https://openalex.org/W2507365558","https://openalex.org/W2523937091","https://openalex.org/W2523993696","https://openalex.org/W2527145521","https://openalex.org/W2527349934","https://openalex.org/W2544271936","https://openalex.org/W2557264465","https://openalex.org/W2559542432","https://openalex.org/W2766520430","https://openalex.org/W2963630207","https://openalex.org/W2963843052","https://openalex.org/W2964241990","https://openalex.org/W3098682680"],"related_works":["https://openalex.org/W3009270862","https://openalex.org/W4389850132","https://openalex.org/W1574724839","https://openalex.org/W2377190948","https://openalex.org/W1495721985","https://openalex.org/W2126270659","https://openalex.org/W2051701434","https://openalex.org/W2096476311","https://openalex.org/W4221117092","https://openalex.org/W4361855866"],"abstract_inverted_index":{"Automatically":[0],"describing":[1],"videos":[2,16,44,77],"with":[3,62,72],"natural":[4,116],"language":[5,112,117],"is":[6,107],"a":[7,30,49,67,84,99,110,134],"crucial":[8],"challenge":[9],"of":[10,41,56],"video":[11,35,60,101,105,124,136,139],"understanding.":[12,140],"Compared":[13],"to":[14,52,70,131,152],"images,":[15],"have":[17],"specific":[18],"spatial-temporal":[19],"structure":[20,55],"and":[21,65,93],"various":[22],"modality":[23,80],"information.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,47,82,97],"propose":[29],"Multirate":[31,50],"Multimodal":[32],"Approach":[33],"for":[34,114,123,138],"captioning.":[36],"Considering":[37],"that":[38],"the":[39,104,148],"speed":[40,74],"motion":[42,73],"in":[43],"varies":[45],"constantly,":[46],"utilize":[48],"GRU":[51],"capture":[53],"temporal":[54],"videos.":[57],"It":[58],"encodes":[59],"frames":[61],"different":[63,79],"intervals":[64],"has":[66],"strong":[68],"ability":[69],"deal":[71],"variance.":[75],"As":[76],"contain":[78],"cues,":[81],"design":[83],"particular":[85],"multimodal":[86],"fusion":[87],"method.":[88],"By":[89],"incorporating":[90],"visual,":[91],"motion,":[92],"topic":[94],"information":[95],"together,":[96],"construct":[98],"well-designed":[100],"representation.":[102],"Then":[103],"representation":[106],"fed":[108],"into":[109],"RNN-based":[111],"model":[113],"generating":[115],"descriptions.":[118],"We":[119],"evaluate":[120],"our":[121,142],"approach":[122,143],"captioning":[125],"on":[126,147],"\"Microsoft":[127],"Research":[128],"-":[129],"Video":[130,151],"Text\"":[132],"(MSR-VTT),":[133],"large-scale":[135],"benchmark":[137],"And":[141],"gets":[144],"great":[145],"performance":[146],"2nd":[149],"MSR":[150],"Language":[153],"Challenge.":[154]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}