{"id":"https://openalex.org/W3000042222","doi":"https://doi.org/10.1109/wacv45572.2020.9093291","title":"Spatio-Temporal Ranked-Attention Networks for Video Captioning","display_name":"Spatio-Temporal Ranked-Attention Networks for Video Captioning","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3000042222","doi":"https://doi.org/10.1109/wacv45572.2020.9093291","mag":"3000042222"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.06127","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024613828","display_name":"Anoop Cherian","orcid":"https://orcid.org/0000-0002-5566-0351"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]},{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP","US"],"is_corresponding":true,"raw_author_name":"Anoop Cherian","raw_affiliation_strings":["Mitsubishi Electric Research Labs, Cambridge, MA","Mitsubishi Electric Research Laboratories,#TAB#"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Labs, Cambridge, MA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories,#TAB#","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440604","display_name":"Jue Wang","orcid":"https://orcid.org/0000-0002-3641-3136"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["AU","JP"],"is_corresponding":false,"raw_author_name":"Jue Wang","raw_affiliation_strings":["Australian National University, Canberra","Mitsubishi Electric Research Laboratories,#TAB#"],"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories,#TAB#","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001601327","display_name":"Chiori Hori","orcid":"https://orcid.org/0000-0002-4201-7578"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Chiori Hori","raw_affiliation_strings":["Mitsubishi Electric Research Labs, Cambridge, MA","Mitsubishi Electric Research Laboratories,#TAB#"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Labs, Cambridge, MA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories,#TAB#","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008369672","display_name":"Tim K. Marks","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Tim K. Marks","raw_affiliation_strings":["Mitsubishi Electric Research Labs, Cambridge, MA","AUSTRALIAN NATIONAL UNIVERSITY"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Labs, Cambridge, MA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"AUSTRALIAN NATIONAL UNIVERSITY","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024613828"],"corresponding_institution_ids":["https://openalex.org/I4210133125","https://openalex.org/I4210159266"],"apc_list":null,"apc_paid":null,"fwci":0.1965,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46980078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1606","last_page":"1615"},"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":0.9991000294685364,"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":0.993399977684021,"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":0.8645037412643433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8246757388114929},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6938897967338562},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6584713459014893},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6167282462120056},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.589314341545105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5326762795448303},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4313371479511261},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3555331826210022},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1856304109096527},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.10857647657394409},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07814428210258484}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8645037412643433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246757388114929},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6938897967338562},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6584713459014893},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6167282462120056},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.589314341545105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5326762795448303},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4313371479511261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3555331826210022},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1856304109096527},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.10857647657394409},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07814428210258484},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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":4,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.06127","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.06127","pdf_url":"https://arxiv.org/pdf/2001.06127","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2001.06127","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.06127","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3000042222","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.06127","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.06127","pdf_url":"https://arxiv.org/pdf/2001.06127","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3000042222.pdf"},"referenced_works_count":97,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1586939924","https://openalex.org/W1601567445","https://openalex.org/W1889081078","https://openalex.org/W1905882502","https://openalex.org/W1923404803","https://openalex.org/W1926645898","https://openalex.org/W1945129080","https://openalex.org/W1956340063","https://openalex.org/W1995820507","https://openalex.org/W2064675550","https://openalex.org/W2072160811","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2130942839","https://openalex.org/W2133459682","https://openalex.org/W2136985729","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2152984213","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2172226303","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2251353663","https://openalex.org/W2425121537","https://openalex.org/W2462996230","https://openalex.org/W2471775118","https://openalex.org/W2505728881","https://openalex.org/W2539222059","https://openalex.org/W2553594924","https://openalex.org/W2554906389","https://openalex.org/W2575842049","https://openalex.org/W2584992898","https://openalex.org/W2593116425","https://openalex.org/W2604141702","https://openalex.org/W2606212668","https://openalex.org/W2607119937","https://openalex.org/W2608022654","https://openalex.org/W2613718673","https://openalex.org/W2618799552","https://openalex.org/W2619947201","https://openalex.org/W2737766105","https://openalex.org/W2740388348","https://openalex.org/W2746726611","https://openalex.org/W2755426660","https://openalex.org/W2765658575","https://openalex.org/W2766375149","https://openalex.org/W2766520430","https://openalex.org/W2767863271","https://openalex.org/W2799261915","https://openalex.org/W2948358897","https://openalex.org/W2949376505","https://openalex.org/W2951390634","https://openalex.org/W2962756039","https://openalex.org/W2962865004","https://openalex.org/W2962994439","https://openalex.org/W2963084599","https://openalex.org/W2963177403","https://openalex.org/W2963403868","https://openalex.org/W2963465031","https://openalex.org/W2963524571","https://openalex.org/W2963576560","https://openalex.org/W2963758027","https://openalex.org/W2963916161","https://openalex.org/W2963971014","https://openalex.org/W2964241990","https://openalex.org/W2964308564","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6639432524","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6680336390","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6685322675","https://openalex.org/W6691419566","https://openalex.org/W6725192724","https://openalex.org/W6729190352","https://openalex.org/W6729814214","https://openalex.org/W6729831399","https://openalex.org/W6735368939","https://openalex.org/W6737005002","https://openalex.org/W6739901393","https://openalex.org/W6740863234","https://openalex.org/W6746291806","https://openalex.org/W6746350439","https://openalex.org/W6749210505","https://openalex.org/W6749578958","https://openalex.org/W6750599028","https://openalex.org/W6898505805","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W3009960797","https://openalex.org/W2580896589","https://openalex.org/W3092761888","https://openalex.org/W2972940264","https://openalex.org/W3019301826","https://openalex.org/W2899483532","https://openalex.org/W3177114149","https://openalex.org/W3003858448","https://openalex.org/W3210436169","https://openalex.org/W2998663487","https://openalex.org/W2997142416","https://openalex.org/W2920457288","https://openalex.org/W3045232921","https://openalex.org/W2760000110","https://openalex.org/W2799813539","https://openalex.org/W3180801688","https://openalex.org/W2894669491","https://openalex.org/W2948227815","https://openalex.org/W3046257495","https://openalex.org/W3121989531"],"abstract_inverted_index":{"Generating":[0],"video":[1],"descriptions":[2],"automatically":[3],"is":[4,144],"a":[5,10,51,77,100,107,122],"challenging":[6],"task":[7],"that":[8,21,86,118],"involves":[9],"complex":[11],"interplay":[12],"between":[13,162],"spatio-temporal":[14],"visual":[15],"features":[16,27,94],"and":[17,28,53,67,98,155,165],"language":[18,62],"models.":[19],"Given":[20],"videos":[22,71],"consist":[23],"of":[24],"spatial":[25,66,115],"(frame-level)":[26],"their":[29],"temporal":[30,68,88,125],"evolutions,":[31],"an":[32],"effective":[33],"captioning":[34],"model":[35,57,136],"should":[36],"be":[37],"able":[38],"to":[39,41,70,84,110,137],"attend":[40,111],"these":[42,96],"different":[43,74],"cues":[44],"selectively.":[45],"To":[46],"this":[47],"end,":[48],"we":[49,129],"propose":[50,121],"Spatio-Temporal":[52],"Temporo-Spatial":[54],"(STaTS)":[55],"attention":[56,69,116],"which,":[58],"conditioned":[59],"on":[60,150],"the":[61,93,134,160,163],"state,":[63],"hierarchically":[64],"combines":[65],"in":[72],"two":[73,151],"orders:":[75],"(i)":[76],"spatiotemporal":[78],"(ST)":[79],"sub-model,":[80,103],"which":[81,104,128],"first":[82,105],"attends":[83],"regions":[85],"have":[87],"evolution,":[89],"then":[90,113],"temporally":[91],"pools":[92],"from":[95],"regions;":[97],"(ii)":[99],"temporo-spatial":[101],"(TS)":[102],"decides":[106],"single":[108],"frame":[109],"to,":[112],"applies":[114],"within":[117],"frame.":[119],"We":[120,147],"novel":[123],"LSTM-based":[124],"ranking":[126],"function,":[127],"call":[130],"ranked":[131],"attention,":[132],"for":[133],"ST":[135,164],"capture":[138],"action":[139],"dynamics.":[140],"Our":[141,157],"entire":[142],"framework":[143],"trained":[145],"end-to-end.":[146],"provide":[148],"experiments":[149],"benchmark":[152],"datasets:":[153],"MSVD":[154],"MSR-VTT.":[156],"results":[158],"demonstrate":[159],"synergy":[161],"TS":[166],"modules,":[167],"outperforming":[168],"recent":[169],"state-of-the-art":[170],"methods.":[171]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}