{"id":"https://openalex.org/W2766375149","doi":"https://doi.org/10.1145/3123266.3123448","title":"Learning Multimodal Attention LSTM Networks for Video Captioning","display_name":"Learning Multimodal Attention LSTM Networks for Video Captioning","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2766375149","doi":"https://doi.org/10.1145/3123266.3123448","mag":"2766375149"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3123448","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123448","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":"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/A5020766468","display_name":"Jun Xu","orcid":"https://orcid.org/0000-0001-7170-111X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Xu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["Mircrosoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Mircrosoft Research, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020766468"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":6.4695,"has_fulltext":false,"cited_by_count":184,"citation_normalized_percentile":{"value":0.97914371,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"537","last_page":"545"},"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":0.9990000128746033,"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":0.9919999837875366,"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":0.9080222249031067},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.858464241027832},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7710878849029541},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.706066370010376},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6669288277626038},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.594562292098999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5552303194999695},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.533072292804718},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5303099155426025},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.48786139488220215},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.47706830501556396},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46782368421554565},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.464744508266449},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45896363258361816},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4448186457157135},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2684669494628906},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1442747712135315}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9080222249031067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.858464241027832},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7710878849029541},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.706066370010376},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6669288277626038},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.594562292098999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5552303194999695},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.533072292804718},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5303099155426025},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.48786139488220215},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.47706830501556396},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46782368421554565},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.464744508266449},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45896363258361816},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4448186457157135},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2684669494628906},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1442747712135315},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123266.3123448","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123448","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","score":0.7099999785423279,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8290336390","display_name":null,"funder_award_id":"61525206","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":33,"referenced_works":["https://openalex.org/W877909479","https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1601567445","https://openalex.org/W1686810756","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2016053056","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2117539524","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2139501017","https://openalex.org/W2142521298","https://openalex.org/W2142900973","https://openalex.org/W2154652894","https://openalex.org/W2156303437","https://openalex.org/W2160204597","https://openalex.org/W2164290393","https://openalex.org/W2425121537","https://openalex.org/W2526346186","https://openalex.org/W2552161745","https://openalex.org/W2556388456","https://openalex.org/W2963149042","https://openalex.org/W2963175879","https://openalex.org/W2963576560","https://openalex.org/W2963843052","https://openalex.org/W2964034111","https://openalex.org/W2964241990","https://openalex.org/W6600178264"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Automatic":[0],"generation":[1],"of":[2,150],"video":[3,10,31,74],"caption":[4],"is":[5,11],"a":[6,33,68,109],"challenging":[7],"task":[8],"as":[9,32,52,54],"an":[12],"information-intensive":[13],"media":[14],"with":[15,171],"complex":[16],"variations.":[17],"Most":[18],"existing":[19,130],"methods,":[20],"either":[21],"based":[22],"on":[23,99,155,179],"language":[24],"templates":[25],"or":[26],"sequence":[27,36],"learning,":[28],"have":[29],"treated":[30],"flat":[34],"data":[35],"while":[37],"ignoring":[38],"intrinsic":[39,148],"multimodality":[40],"nature.":[41],"Observing":[42],"that":[43,132,163],"different":[44,120,139],"modalities":[45,122],"(e.g.,":[46],"frame,":[47],"motion,":[48],"and":[49,93,160,175],"audio":[50],"streams),":[51],"well":[53],"the":[55,63,103,115,124,134,147,168],"elements":[56,101],"within":[57],"each":[58],"modality,":[59],"contribute":[60],"differently":[61],"to":[62,72,96,117,123,145],"sentence":[64,104],"generation,":[65],"we":[66,107,141],"present":[67],"novel":[69,110],"deep":[70],"framework":[71],"boost":[73],"captioning":[75],"by":[76],"learning":[77],"Multimodal":[78],"Attention":[79],"Long-Short":[80],"Term":[81],"Memory":[82],"networks":[83],"(MA-LSTM).":[84],"Our":[85],"proposed":[86],"MA-LSTM":[87,116,165],"fully":[88],"exploits":[89],"both":[90],"multimodal":[91],"streams":[92],"temporal":[94],"attention":[95],"selectively":[97],"focus":[98],"specific":[100],"during":[102],"generation.":[105],"Moreover,":[106],"design":[108],"child-sum":[111],"fusion":[112],"unit":[113],"in":[114],"effectively":[118],"combine":[119],"encoded":[121],"initial":[125],"decoding":[126],"states.":[127],"Different":[128],"from":[129],"approaches":[131],"employ":[133],"same":[135],"LSTM":[136,144],"structure":[137],"for":[138],"modalities,":[140],"train":[142],"modality-specific":[143],"capture":[146],"representations":[149],"individual":[151],"modalities.":[152],"The":[153],"experiments":[154],"two":[156],"benchmark":[157],"datasets":[158],"(MSVD":[159],"MSR-VTT)":[161],"show":[162],"our":[164],"significantly":[166],"outperforms":[167],"state-of-the-art":[169],"methods":[170],"52.3":[172],"[email":[173],"protected]":[174],"70.4":[176],"CIDER-D":[177],"metrics":[178],"MSVD":[180],"dataset,":[181],"respectively.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":42},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":32},{"year":2018,"cited_by_count":10}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}