{"id":"https://openalex.org/W1578531252","doi":"https://doi.org/10.1109/icip.2003.1246957","title":"Video caption detection and extraction using temporal information","display_name":"Video caption detection and extraction using temporal information","publication_year":2004,"publication_date":"2004-06-21","ids":{"openalex":"https://openalex.org/W1578531252","doi":"https://doi.org/10.1109/icip.2003.1246957","mag":"1578531252"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2003.1246957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2003.1246957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)","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/A5052233895","display_name":"Bo Luo","orcid":"https://orcid.org/0000-0001-8196-2436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Luo","raw_affiliation_strings":["Department of Information Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110380387","display_name":"Xiaoou Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoou Tang","raw_affiliation_strings":["Department of Information Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039205892","display_name":"Jianzhuang Liu","orcid":"https://orcid.org/0000-0002-7960-9382"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhuang Liu","raw_affiliation_strings":["Department of Information Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100397026","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0003-1991-119X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjiang Zhang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052233895"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.6398,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.84253563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"297"},"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":0.995199978351593,"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":0.9818000197410583,"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":0.8422943353652954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.659274697303772},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.585401177406311},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5160441398620605},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5074183344841003},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.48705175518989563},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46350306272506714},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.46318814158439636},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.42861780524253845},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.42381569743156433},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.3539341688156128},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3481943607330322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8422943353652954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.659274697303772},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.585401177406311},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5160441398620605},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5074183344841003},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.48705175518989563},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46350306272506714},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.46318814158439636},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.42861780524253845},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.42381569743156433},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3539341688156128},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3481943607330322},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip.2003.1246957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2003.1246957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.8571","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.8571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.eecs.ku.edu/~bluo/download/luo03icip.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1480779007","https://openalex.org/W1900606880","https://openalex.org/W1962397371","https://openalex.org/W1972774730","https://openalex.org/W2019995264","https://openalex.org/W2085425470","https://openalex.org/W2090874155","https://openalex.org/W2097003509","https://openalex.org/W2107169849","https://openalex.org/W2114449851","https://openalex.org/W2117586922","https://openalex.org/W2120980417","https://openalex.org/W2131093082","https://openalex.org/W2137542411","https://openalex.org/W2149032327","https://openalex.org/W2168026884","https://openalex.org/W2170048334","https://openalex.org/W6677706482","https://openalex.org/W6679382745","https://openalex.org/W6682286075","https://openalex.org/W6684492262"],"related_works":["https://openalex.org/W4389850132","https://openalex.org/W1574724839","https://openalex.org/W2377190948","https://openalex.org/W2096476311","https://openalex.org/W4221117092","https://openalex.org/W4361855866","https://openalex.org/W1965900363","https://openalex.org/W169721953","https://openalex.org/W2899854151","https://openalex.org/W1623638113"],"abstract_inverted_index":{"Video":[0],"caption":[1],"detection":[2],"and":[3],"extraction":[4],"is":[5],"an":[6],"important":[7],"step":[8],"for":[9],"information":[10,21,29],"retrieval":[11],"in":[12,22,31,51],"video":[13,23,43,74],"databases.":[14],"In":[15],"this":[16],"paper,":[17],"we":[18,35,54,64],"extract":[19,65],"text":[20],"by":[24],"fully":[25],"utilizing":[26],"the":[27,32,47,52,58,66,73],"temporal":[28],"contained":[30],"video.":[33],"First":[34],"create":[36,69],"a":[37,42,70],"binary":[38],"abstract":[39],"sequence":[40],"from":[41],"segment.":[44,75],"By":[45],"analyzing":[46],"statistical":[48],"pixel":[49],"changes":[50],"sequence,":[53],"can":[55],"effectively":[56],"locate":[57],"(dis)appealing":[59],"frames":[60],"of":[61,72],"captions.":[62],"Finally":[63],"captions":[67],"to":[68],"summary":[71]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
