{"id":"https://openalex.org/W2145463354","doi":"https://doi.org/10.1109/mmsp.2002.1203344","title":"The latest achievement of VC project for automatic video caption generation","display_name":"The latest achievement of VC project for automatic video caption generation","publication_year":2004,"publication_date":"2004-01-24","ids":{"openalex":"https://openalex.org/W2145463354","doi":"https://doi.org/10.1109/mmsp.2002.1203344","mag":"2145463354"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2002.1203344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2002.1203344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE Workshop on Multimedia Signal Processing.","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/A5102915819","display_name":"Takashi Suzuki","orcid":"https://orcid.org/0000-0002-8467-0663"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"T. Suzuki","raw_affiliation_strings":["Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan","Graduate Sch. of Comput. Sci. & Eng., Aizu Univ., Fukushima, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]},{"raw_affiliation_string":"Graduate Sch. of Comput. Sci. & Eng., Aizu Univ., Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003481466","display_name":"T. Kitazume","orcid":null},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Kitazume","raw_affiliation_strings":["Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan","Graduate Sch. of Comput. Sci. & Eng., Aizu Univ., Fukushima, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]},{"raw_affiliation_string":"Graduate Sch. of Comput. Sci. & Eng., Aizu Univ., Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028205065","display_name":"Masaaki Sugiyama","orcid":"https://orcid.org/0000-0003-2416-1426"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Sugiyama","raw_affiliation_strings":["Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan","Graduate Sch. of Comput. Sci. & Eng., Aizu Univ., Fukushima, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]},{"raw_affiliation_string":"Graduate Sch. of Comput. Sci. & Eng., Aizu Univ., Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102915819"],"corresponding_institution_ids":["https://openalex.org/I141591182"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17701803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"456","last_page":"459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9769999980926514,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9769999980926514,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9537000060081482,"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"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9305999875068665,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8163164854049683},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.6678194999694824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6081507205963135},{"id":"https://openalex.org/keywords/symbol","display_name":"Symbol (formal)","score":0.5250625014305115},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4734587073326111},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4312693178653717},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16931533813476562},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.06934571266174316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163164854049683},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.6678194999694824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6081507205963135},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.5250625014305115},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4734587073326111},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4312693178653717},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16931533813476562},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.06934571266174316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2002.1203344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2002.1203344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE Workshop on Multimedia Signal Processing.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1904714900","https://openalex.org/W2572669069"],"related_works":["https://openalex.org/W4385386698","https://openalex.org/W4388119604","https://openalex.org/W2954418080","https://openalex.org/W3121570353","https://openalex.org/W818235636","https://openalex.org/W4388119676","https://openalex.org/W1566913699","https://openalex.org/W2081328318","https://openalex.org/W2043722775","https://openalex.org/W3034799230"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,87,92],"progress":[4],"of":[5,32,86],"our":[6],"automatic":[7],"video":[8,16,39],"caption":[9,17],"generation":[10],"project.":[11],"VC":[12],"project":[13],"has":[14,43,73],"developed":[15,63],"markup":[18],"language":[19],"and":[20,24,30,52,68,81,102],"its":[21,41],"player":[22],"(VCML":[23],"VCML":[25,35,56],"player)":[26],"to":[27,64],"reduce":[28],"labor":[29],"cost":[31],"making":[33],"captions.":[34],"player,":[36],"which":[37,60],"displays":[38],"with":[40],"caption,":[42],"new":[44],"functions.":[45],"One":[46],"is":[47,54],"displaying":[48],"auditory":[49],"scene":[50],"symbol,":[51],"another":[53],"tree-structured":[55],"files.":[57],"Voice-pause":[58],"method,":[59,94,96],"was":[61],"originally":[62],"align":[65,98],"voice":[66,80],"intervals":[67,104],"their":[69],"corresponding":[70],"written":[71],"text,":[72],"been":[74],"improved":[75,93],"sound":[76],"data":[77],"containing":[78],"both":[79],"music":[82,101],"intervals.":[83],"The":[84],"results":[85],"alignment":[88],"experiment":[89],"show":[90],"that":[91],"voice-music-pause":[95],"can":[97],"all":[99],"voice,":[100],"pause":[103],"effectively.":[105]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
