{"id":"https://openalex.org/W4385270576","doi":"https://doi.org/10.1109/uv56588.2022.10185501","title":"Enhanced Video Caption Generation Based on Multimodal Features","display_name":"Enhanced Video Caption Generation Based on Multimodal Features","publication_year":2022,"publication_date":"2022-10-22","ids":{"openalex":"https://openalex.org/W4385270576","doi":"https://doi.org/10.1109/uv56588.2022.10185501"},"language":"en","primary_location":{"id":"doi:10.1109/uv56588.2022.10185501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/uv56588.2022.10185501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 6th International Conference on Universal Village (UV)","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/A5051451340","display_name":"Xuefei Huang","orcid":"https://orcid.org/0000-0002-8670-1283"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Xuefei Huang","raw_affiliation_strings":["Macao Polytechnic University,Faculty of Applied Sciences,Macao,China","Faculty of Applied Sciences, Macao Polytechnic University, Macao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Faculty of Applied Sciences,Macao,China","institution_ids":["https://openalex.org/I49835588"]},{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, Macao, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019419036","display_name":"Wei Ke","orcid":"https://orcid.org/0000-0003-0952-0961"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Wei Ke","raw_affiliation_strings":["Macao Polytechnic University,Faculty of Applied Sciences,Macao,China","Faculty of Applied Sciences, Macao Polytechnic University, Macao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University,Faculty of Applied Sciences,Macao,China","institution_ids":["https://openalex.org/I49835588"]},{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, Macao, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100627101","display_name":"Hao Sheng","orcid":"https://orcid.org/0000-0002-2811-8962"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Sheng","raw_affiliation_strings":["Beihang University,School of Computer Science and Engineering,Beijing,China","School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4061,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61639966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.8701990246772766},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6799850463867188},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5227929949760437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5170838832855225},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.47349199652671814},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44654443860054016},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4406471848487854},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.432380735874176},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.41393494606018066},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34413063526153564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8701990246772766},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6799850463867188},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5227929949760437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5170838832855225},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.47349199652671814},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44654443860054016},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4406471848487854},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.432380735874176},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.41393494606018066},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34413063526153564},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/uv56588.2022.10185501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/uv56588.2022.10185501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 6th International Conference on Universal Village (UV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8600000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326978","display_name":"State Key Laboratory of Software Development Environment","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1492731187","https://openalex.org/W1522734439","https://openalex.org/W1895577753","https://openalex.org/W1983364832","https://openalex.org/W2064675550","https://openalex.org/W2139501017","https://openalex.org/W2164290393","https://openalex.org/W2425121537","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2896457183","https://openalex.org/W2913822893","https://openalex.org/W2919115771","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2964065937","https://openalex.org/W2964241990","https://openalex.org/W2975357369","https://openalex.org/W3009960797","https://openalex.org/W3047922786","https://openalex.org/W3095821074","https://openalex.org/W3109395208","https://openalex.org/W3155562891","https://openalex.org/W3190858484","https://openalex.org/W3203464874","https://openalex.org/W4285134614","https://openalex.org/W4287777632","https://openalex.org/W4288054401","https://openalex.org/W4297192905","https://openalex.org/W4303183332","https://openalex.org/W4394659899","https://openalex.org/W6629393784","https://openalex.org/W6680145277","https://openalex.org/W6684090549","https://openalex.org/W6755207826","https://openalex.org/W6767853649","https://openalex.org/W6777481484","https://openalex.org/W6843348751","https://openalex.org/W6864544085"],"related_works":["https://openalex.org/W2035104213","https://openalex.org/W3196817267","https://openalex.org/W1976600725","https://openalex.org/W2240967841","https://openalex.org/W2791686160","https://openalex.org/W1513257435","https://openalex.org/W2289840258","https://openalex.org/W2503352526","https://openalex.org/W2968405290","https://openalex.org/W2960696728"],"abstract_inverted_index":{"Video":[0],"caption":[1,102],"is":[2,91,130],"the":[3,10,60,65,72,117,128,134],"automatically":[4],"generated":[5,120],"of":[6,55,59,68,85,119],"abstract":[7],"expressions":[8],"for":[9],"content":[11],"contained":[12],"in":[13,34,109],"videos.":[14],"It":[15],"involves":[16],"two":[17],"important":[18,74],"fields":[19],"\u2014":[20],"computer":[21],"vision":[22],"and":[23,27,111],"natural":[24],"language":[25],"processing,":[26],"has":[28,39],"become":[29],"a":[30,92,100],"considerable":[31],"research":[32],"topic":[33],"smart":[35],"life.":[36],"Deep":[37],"learning":[38],"successfully":[40],"contributed":[41],"to":[42,80,115],"this":[43,96],"task":[44],"with":[45],"good":[46],"results.":[47],"As":[48],"we":[49,98],"know,":[50],"video":[51,101],"contains":[52],"various":[53],"modals":[54],"information,":[56],"yet":[57],"most":[58],"existing":[61],"solutions":[62],"start":[63],"from":[64,82],"visual":[66,89],"perspective":[67],"video,":[69],"while":[70],"ignoring":[71],"equally":[73],"audio":[75],"modal":[76],"information.":[77],"Therefore,":[78],"how":[79],"benefit":[81],"additional":[83],"forms":[84],"cues":[86],"other":[87],"than":[88],"information":[90],"huge":[93],"challenge.":[94],"In":[95],"work,":[97],"propose":[99],"generation":[103],"method":[104,129],"that":[105,127],"fuses":[106],"multimodal":[107],"features":[108],"videos,":[110],"adds":[112],"attention":[113],"mechanism":[114],"improve":[116],"quality":[118],"description":[121],"sentences.":[122],"The":[123],"experimental":[124],"results":[125],"demonstrate":[126],"well":[131],"validated":[132],"on":[133],"MSR-VTT":[135],"dataset.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}