{"id":"https://openalex.org/W2151793464","doi":"https://doi.org/10.1109/mmsp.2002.1203234","title":"Personalized video summary using visual semantic annotations and automatic speech transcriptions","display_name":"Personalized video summary using visual semantic annotations and automatic speech transcriptions","publication_year":2004,"publication_date":"2004-01-23","ids":{"openalex":"https://openalex.org/W2151793464","doi":"https://doi.org/10.1109/mmsp.2002.1203234","mag":"2151793464"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2002.1203234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2002.1203234","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/A5034229341","display_name":"B.L. Tseng","orcid":"https://orcid.org/0009-0004-1720-4832"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"B.L. Tseng","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Hawthorne, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Hawthorne, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109855094","display_name":"Ching\u2010Yung Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ching-Yung Lin","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Hawthorne, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Hawthorne, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034229341"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":1.6398,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85596916,"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":"5","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T11439","display_name":"Video Analysis and Summarization","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9894000291824341,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8865858316421509},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.7640240788459778},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7312511205673218},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6598228812217712},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5661555528640747},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4784236550331116},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4259820282459259},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4186221957206726},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3641303479671478},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34403353929519653},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34126341342926025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8865858316421509},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7640240788459778},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7312511205673218},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6598228812217712},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5661555528640747},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4784236550331116},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4259820282459259},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4186221957206726},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3641303479671478},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34403353929519653},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34126341342926025},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2002.1203234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2002.1203234","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1974812781","https://openalex.org/W2093250015","https://openalex.org/W2115541970","https://openalex.org/W2123867584","https://openalex.org/W2137391055","https://openalex.org/W2143092130","https://openalex.org/W4285719527","https://openalex.org/W6677096176","https://openalex.org/W6678112719","https://openalex.org/W6680532617"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W2973759123","https://openalex.org/W1517524280"],"abstract_inverted_index":{"A":[0],"personalized":[1,126],"video":[2,9,82,127],"summary":[3,12,100],"is":[4],"dynamically":[5],"generated":[6],"in":[7,29,73],"our":[8],"personalization":[10,23,69],"and":[11,18,34,64,70,88,103,107,116,122],"system":[13,24],"based":[14],"on":[15],"user":[16,92,104],"preference":[17,105],"usage":[19],"environment.":[20],"The":[21,42,94],"three-tier":[22],"adopts":[25],"the":[26,40,45,58,74,77,97,112],"server-middleware-client":[27],"architecture":[28],"order":[30],"maintain,":[31],"select,":[32],"adapt,":[33],"deliver":[35],"rich":[36],"media":[37],"content":[38,46],"to":[39],"user.":[41],"server":[43],"stores":[44],"sources":[47],"along":[48],"with":[49,91],"their":[50],"corresponding":[51],"MPEG-7":[52],"metadata":[53,59],"descriptions.":[54],"In":[55],"this":[56],"paper,":[57],"includes":[60,96],"visual":[61,114],"semantic":[62],"annotations":[63,87],"automatic":[65],"speech":[66],"transcriptions.":[67],"Our":[68],"summarization":[71],"engine":[72],"middleware":[75],"selects":[76],"optimal":[78],"set":[79],"of":[80],"desired":[81],"segments":[83,119],"by":[84],"matching":[85,106],"shot":[86,115],"sentence":[89,118],"transcripts":[90],"preferences.":[93],"process":[95],"shot-to-sentence":[98],"alignment,":[99],"segment":[101],"selection,":[102],"propagation.":[108],"As":[109],"a":[110,125],"result,":[111],"relevant":[113],"audio":[117],"are":[120],"aggregated":[121],"composed":[123],"into":[124],"summary.":[128]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
