{"id":"https://openalex.org/W2560346187","doi":"https://doi.org/10.1162/tacl_a_00013","title":"Video Captioning with Multi-Faceted Attention","display_name":"Video Captioning with Multi-Faceted Attention","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2560346187","doi":"https://doi.org/10.1162/tacl_a_00013","mag":"2560346187"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00013","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00013","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00013","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00013","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045357216","display_name":"Xiang Long","orcid":"https://orcid.org/0000-0002-0589-8839"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Long","raw_affiliation_strings":["Tsinghua University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040877128","display_name":"Chuang Gan","orcid":"https://orcid.org/0000-0003-4031-5886"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chuang Gan","raw_affiliation_strings":["Tsinghua University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085818578","display_name":"Gerard de Melo","orcid":"https://orcid.org/0000-0002-2930-2059"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Gerard de Melo","raw_affiliation_strings":["Rutgers University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,","institution_ids":["https://openalex.org/I4210096112"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040877128","https://openalex.org/A5045357216","https://openalex.org/A5085818578"],"corresponding_institution_ids":["https://openalex.org/I4210096112","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":5.7224,"has_fulltext":true,"cited_by_count":86,"citation_normalized_percentile":{"value":0.97064623,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"6","issue":null,"first_page":"173","last_page":"184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9962999820709229,"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":0.993399977684021,"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":0.9607329368591309},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9150387048721313},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7869590520858765},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6587556600570679},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5716271996498108},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5269473195075989},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48568853735923767},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4528849124908447},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4528560936450958},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.43102771043777466},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36948347091674805},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33866554498672485},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2680850625038147}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9607329368591309},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9150387048721313},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7869590520858765},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6587556600570679},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5716271996498108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5269473195075989},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48568853735923767},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4528849124908447},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4528560936450958},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.43102771043777466},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36948347091674805},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33866554498672485},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2680850625038147},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00013","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00013","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00013","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c1118201c6a34d1ba9d54a6c96bd400e","is_oa":false,"landing_page_url":"https://doaj.org/article/c1118201c6a34d1ba9d54a6c96bd400e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 6 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00013","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00013","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00013","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2560346187.pdf","grobid_xml":"https://content.openalex.org/works/W2560346187.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1527575280","https://openalex.org/W1573040851","https://openalex.org/W1586051859","https://openalex.org/W1586939924","https://openalex.org/W1606347560","https://openalex.org/W1714639292","https://openalex.org/W1836465849","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2016053056","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2110485445","https://openalex.org/W2122180654","https://openalex.org/W2122476475","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2131988669","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2150355110","https://openalex.org/W2157331557","https://openalex.org/W2164290393","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2251117008","https://openalex.org/W2302086703","https://openalex.org/W2509282593","https://openalex.org/W2740284552","https://openalex.org/W2789221157","https://openalex.org/W2962706528","https://openalex.org/W2963331233","https://openalex.org/W2963410018","https://openalex.org/W2963576560","https://openalex.org/W2963843052","https://openalex.org/W2964199361","https://openalex.org/W2964241990","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"has":[2],"attracted":[3],"an":[4],"increasing":[5],"amount":[6],"of":[7,28,40,56,97,130],"interest,":[8],"due":[9],"in":[10,127],"part":[11],"to":[12,51,76,133],"its":[13],"potential":[14],"for":[15,92],"improved":[16],"accessibility":[17],"and":[18,31,48,59,87,95,113,123,136],"information":[19],"retrieval.":[20],"While":[21],"existing":[22],"methods":[23],"rely":[24],"on":[25,66,109],"different":[26],"kinds":[27],"visual":[29,57,82],"features":[30,58,83,135],"model":[32],"architectures,":[33],"they":[34],"do":[35],"not":[36],"make":[37],"full":[38],"use":[39],"pertinent":[41],"semantic":[42,60,85],"cues.":[43],"We":[44],"present":[45],"a":[46],"unified":[47],"extensible":[49],"framework":[50,119],"jointly":[52],"leverage":[53],"multiple":[54],"sorts":[55],"attributes.":[61,137],"Our":[62],"novel":[63],"architecture":[64],"builds":[65],"LSTMs":[67],"with":[68],"two":[69],"multi-faceted":[70],"attention":[71],"layers.":[72],"These":[73],"first":[74],"learn":[75],"automatically":[77],"select":[78],"the":[79,93,98,110,128,134],"most":[80],"salient":[81],"or":[84],"attributes,":[86],"then":[88],"yield":[89],"overall":[90],"representations":[91],"input":[94],"output":[96],"sentence":[99],"generation":[100],"component":[101],"via":[102],"custom":[103],"feature":[104],"scaling":[105],"operations.":[106],"Experimental":[107],"results":[108],"challenging":[111],"MSVD":[112],"MSR-VTT":[114],"datasets":[115],"show":[116],"that":[117],"our":[118],"outperforms":[120],"previous":[121],"work":[122],"performs":[124],"robustly":[125],"even":[126],"presence":[129],"added":[131],"noise":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}