{"id":"https://openalex.org/W4288083805","doi":"https://doi.org/10.1145/3355390","title":"Video Description","display_name":"Video Description","publication_year":2019,"publication_date":"2019-10-16","ids":{"openalex":"https://openalex.org/W4288083805","doi":"https://doi.org/10.1145/3355390"},"language":"en","primary_location":{"id":"doi:10.1145/3355390","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3355390","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3355390","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"review","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3355390","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003668441","display_name":"Nayyer Aafaq","orcid":"https://orcid.org/0000-0003-2763-2094"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Nayyer Aafaq","raw_affiliation_strings":["The University of Western Australia, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089986388","display_name":"Ajmal Mian","orcid":"https://orcid.org/0000-0002-5206-3842"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ajmal Mian","raw_affiliation_strings":["The University of Western Australia, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641142","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-7409-0948"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["The University of Western Australia, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075172808","display_name":"Syed Zulqarnain Gilani","orcid":"https://orcid.org/0000-0002-7448-2327"},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]},{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Syed Zulqarnain Gilani","raw_affiliation_strings":["The University of Western Australia and Edith Cowan University"],"affiliations":[{"raw_affiliation_string":"The University of Western Australia and Edith Cowan University","institution_ids":["https://openalex.org/I12079687","https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080823547","display_name":"Mubarak Shah","orcid":"https://orcid.org/0000-0001-6172-5572"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mubarak Shah","raw_affiliation_strings":["University of Central Florida, Orlando, Florida, USA"],"affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003668441"],"corresponding_institution_ids":["https://openalex.org/I177877127"],"apc_list":null,"apc_paid":null,"fwci":6.7429,"has_fulltext":true,"cited_by_count":145,"citation_normalized_percentile":{"value":0.97479389,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"52","issue":"6","first_page":"1","last_page":"37"},"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":0.9958999752998352,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8955710530281067},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6432411074638367},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6068959832191467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5676101446151733},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5316287279129028},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46468284726142883},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42162394523620605},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4171050190925598},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.41374754905700684},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36305344104766846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8955710530281067},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6432411074638367},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6068959832191467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5676101446151733},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5316287279129028},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46468284726142883},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42162394523620605},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4171050190925598},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.41374754905700684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36305344104766846},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3355390","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3355390","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3355390","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3355390","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3355390","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3355390","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8600000143051147}],"awards":[{"id":"https://openalex.org/G2279853913","display_name":null,"funder_award_id":"W911NF-19-1","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G6602293961","display_name":null,"funder_award_id":"W911NF-19-1-0356","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8415477955","display_name":null,"funder_award_id":"W911NF-19","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8998121839","display_name":null,"funder_award_id":"911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4288083805.pdf","grobid_xml":"https://content.openalex.org/works/W4288083805.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W877909479","https://openalex.org/W1601567445","https://openalex.org/W1964575408","https://openalex.org/W2009757081","https://openalex.org/W2024932032","https://openalex.org/W2031489346","https://openalex.org/W2060242122","https://openalex.org/W2064675550","https://openalex.org/W2111078031","https://openalex.org/W2117539524","https://openalex.org/W2128856065","https://openalex.org/W2131774270","https://openalex.org/W2134518303","https://openalex.org/W2143668817","https://openalex.org/W2145339207","https://openalex.org/W2152984213","https://openalex.org/W2168356304","https://openalex.org/W2185175083","https://openalex.org/W2251353663","https://openalex.org/W2523937091","https://openalex.org/W2564590796","https://openalex.org/W2565656701","https://openalex.org/W2600463316","https://openalex.org/W2607151106","https://openalex.org/W2914699769","https://openalex.org/W2962937869","https://openalex.org/W2963410018","https://openalex.org/W2963613897","https://openalex.org/W2963916161","https://openalex.org/W2963971014","https://openalex.org/W2964199361","https://openalex.org/W2964241990","https://openalex.org/W3011957837","https://openalex.org/W3030514670","https://openalex.org/W3124386704","https://openalex.org/W4205969993"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Video":[0],"description":[1,139,208,223],"is":[2,210,225,229],"the":[3,12,25,46,69,72,90,94,120,155,167,193,204,217,233,240,244,249,272],"automatic":[4],"generation":[5],"of":[6,14,39,49,109,113,124,157,183,221,239,261,270,279],"natural":[7,56],"language":[8,57,149,246],"sentences":[9],"that":[10,161,186,202,278],"describe":[11],"contents":[13],"a":[15,37,75,98,179],"given":[16],"video.":[17],"It":[18],"has":[19],"applications":[20],"in":[21,41,52,68,82,107,169,196,212,248],"human-robot":[22],"interaction,":[23],"helping":[24],"visually":[26],"impaired":[27],"and":[28,55,62,115,118,122,135,144,243],"video":[29,138,197,207,222],"subtitling.":[30],"The":[31],"past":[32],"few":[33],"years":[34],"have":[35,65],"seen":[36],"surge":[38],"research":[40,80,209,289],"this":[42,83],"area":[43],"due":[44,215],"to":[45,78,151,216,231],"unprecedented":[47],"success":[48],"deep":[50,101,191],"learning":[51,102],"computer":[53],"vision":[54],"processing.":[58],"Numerous":[59],"methods,":[60],"datasets,":[61],"evaluation":[63,126,266],"metrics":[64,267],"been":[66],"proposed":[67],"literature,":[70],"calling":[71],"need":[73],"for":[74],"comprehensive":[76],"survey":[77,200,284],"focus":[79,99],"efforts":[81],"flourishing":[84],"new":[85],"direction.":[86],"This":[87],"article":[88],"fills":[89],"gap":[91],"by":[92,178,285],"surveying":[93],"state-of-the-art":[95,195],"approaches":[96,140,175],"with":[97,147,166,190,277],"on":[100],"models;":[103],"comparing":[104],"benchmark":[105],"datasets":[106,159,253],"terms":[108],"their":[110],"domains,":[111],"number":[112],"classes,":[114],"repository":[116],"size;":[117],"identifying":[119],"pros":[121],"cons":[123],"various":[125],"metrics,":[127],"such":[128],"as":[129],"SPICE,":[130],"CIDEr,":[131],"ROUGE,":[132],"BLEU,":[133],"METEOR,":[134],"WMD.":[136],"Classical":[137,174],"combined":[141],"subject,":[142],"object,":[143],"verb":[145],"detection":[146],"template-based":[148],"models":[150,224],"generate":[152],"sentences.":[153],"However,":[154],"release":[156],"large":[158],"revealed":[160],"these":[162],"methods":[163,185],"cannot":[164],"cope":[165],"diversity":[168,258],"unconstrained":[170],"open":[171],"domain":[172],"videos.":[173],"were":[176,187],"followed":[177],"very":[180],"short":[181,269],"era":[182],"statistical":[184],"soon":[188],"replaced":[189],"learning,":[192],"current":[194,265],"description.":[198,251],"Our":[199],"shows":[201],"despite":[203],"fast-paced":[205],"developments,":[206],"still":[211],"its":[213],"infancy":[214],"following":[218],"reasons:":[219],"Analysis":[220],"challenging,":[226],"because":[227],"it":[228],"difficult":[230],"ascertain":[232],"contributions":[234],"towards":[235],"accuracy":[236],"or":[237],"errors":[238],"visual":[241,257],"features":[242],"adopted":[245],"model":[247],"final":[250],"Existing":[252],"neither":[254],"contain":[255],"adequate":[256],"nor":[259],"complexity":[260],"linguistic":[262],"structures.":[263],"Finally,":[264],"fall":[268],"measuring":[271],"agreement":[273],"between":[274],"machine-generated":[275],"descriptions":[276],"humans.":[280],"We":[281],"conclude":[282],"our":[283],"listing":[286],"promising":[287],"future":[288],"directions.":[290]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2022-07-28T00:00:00"}