{"id":"https://openalex.org/W4388821239","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317231","title":"Exploring a CLIP-Enhanced Automated Approach for Video Description Generation","display_name":"Exploring a CLIP-Enhanced Automated Approach for Video Description Generation","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821239","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317231"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317231","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5111077053","display_name":"Siang-Ling Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Siang-Ling Zhang","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109656923","display_name":"Huai-Hsun Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Huai-Hsun Cheng","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102102478","display_name":"Yen-Hsin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yen-Hsin Chen","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018553457","display_name":"Mei-Chen Yeh","orcid":"https://orcid.org/0000-0001-8665-7860"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Mei-Chen Yeh","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14426247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1506","last_page":"1511"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9947999715805054,"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":0.9883999824523926,"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":0.981726884841919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8379360437393188},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.6341050863265991},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.6339548230171204},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5979390144348145},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.562791645526886},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5558303594589233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5270735621452332},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5077958703041077},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44381698966026306},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3282730281352997},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1964987814426422},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10888352990150452},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.09720471501350403}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.981726884841919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8379360437393188},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.6341050863265991},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.6339548230171204},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5979390144348145},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.562791645526886},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5558303594589233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5270735621452332},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5077958703041077},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44381698966026306},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3282730281352997},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1964987814426422},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10888352990150452},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.09720471501350403},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317231","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8500000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1956340063","https://openalex.org/W2133459682","https://openalex.org/W2560313346","https://openalex.org/W2795840542","https://openalex.org/W2883910824","https://openalex.org/W2904658088","https://openalex.org/W2964110616","https://openalex.org/W2995753487","https://openalex.org/W3025136821","https://openalex.org/W3025796084","https://openalex.org/W3035372819","https://openalex.org/W3094502228","https://openalex.org/W3135367836","https://openalex.org/W3150558292","https://openalex.org/W3166396011","https://openalex.org/W3194973321","https://openalex.org/W4282048378","https://openalex.org/W4308234126","https://openalex.org/W4318718936","https://openalex.org/W4320458302","https://openalex.org/W6791353385","https://openalex.org/W6803283611"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Visual":[0],"storytelling":[1],"is":[2],"a":[3,57],"learned":[4],"ability":[5],"that":[6,82,126],"humans":[7],"have":[8],"developed":[9],"through":[10,31],"the":[11,49,79,105,120,127],"course":[12],"of":[13,28,51,78,138],"their":[14,29],"evolution.":[15],"In":[16,86],"contrast":[17],"to":[18,53,99],"written":[19],"records":[20],"and":[21,40,61],"descriptions,":[22],"people":[23],"are":[24],"now":[25],"sharing":[26],"glimpses":[27],"lives":[30],"short":[32],"videos.":[33],"Human":[34],"conversations":[35],"largely":[36],"rely":[37],"on":[38,119],"visual":[39,60,97],"auditory":[41],"inputs,":[42],"followed":[43],"by":[44],"corresponding":[45],"feedbacks.":[46],"For":[47],"machines,":[48],"conversion":[50],"images":[52],"texts":[54],"serves":[55],"as":[56,109,111],"bridge":[58],"between":[59],"linguistic":[62],"information,":[63],"enabling":[64],"machine-human":[65],"interactions":[66],"more":[67],"naturally.":[68],"Video":[69],"captioning\u2014involving":[70],"automatically":[71],"generating":[72],"textual":[73,101],"descriptions":[74],"from":[75],"videos\u2014is":[76],"one":[77],"core":[80],"technologies":[81],"enable":[83],"such":[84],"applications.":[85],"this":[87,115],"work,":[88],"we":[89,124],"present":[90],"CLIP-CAP,":[91],"an":[92],"automatic":[93],"method":[94],"for":[95],"transforming":[96],"contents":[98],"concise":[100],"descriptions.":[102],"We":[103],"investigate":[104],"CLIP":[106],"pretraining":[107],"model":[108,130],"well":[110],"its":[112],"potential":[113],"in":[114,136],"task.":[116],"Through":[117],"experiments":[118],"ActivityNet":[121],"Captions":[122],"dataset,":[123],"show":[125],"proposed":[128],"CLIP-CAP":[129],"outperforms":[131],"existing":[132],"video":[133],"captioning":[134],"methods":[135],"terms":[137],"several":[139],"different":[140],"metrics.":[141]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
