{"id":"https://openalex.org/W4230262033","doi":"https://doi.org/10.1109/icpr.2004.1334156","title":"A novel video caption detection approach using multi-frame integration","display_name":"A novel video caption detection approach using multi-frame integration","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W4230262033","doi":"https://doi.org/10.1109/icpr.2004.1334156"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2004.1334156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2004.1334156","pdf_url":null,"source":{"id":"https://openalex.org/S4363608750","display_name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100733177","display_name":"Rongrong Wang","orcid":"https://orcid.org/0000-0002-6098-5417"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065682828","display_name":"Wanjun Jin","orcid":"https://orcid.org/0009-0000-4777-5581"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanjun Jin","raw_affiliation_strings":["Department of Computer Science and Engineering, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102516427","display_name":"Lide Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lide Wu","raw_affiliation_strings":["Department of Computer Science and Engineering, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.6647,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.84987893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"449","last_page":"452 Vol.1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8047189116477966},{"id":"https://openalex.org/keywords/sobel-operator","display_name":"Sobel operator","score":0.701339066028595},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6751300692558289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6675133109092712},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5699257850646973},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5178449749946594},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5158683657646179},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.49455997347831726},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4443759322166443},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.44059643149375916},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43650615215301514},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.42688918113708496},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.4225963354110718},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4194572865962982},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3831520676612854},{"id":"https://openalex.org/keywords/edge-detection","display_name":"Edge detection","score":0.35531359910964966},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.2013091742992401},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10482534766197205}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047189116477966},{"id":"https://openalex.org/C30703548","wikidata":"https://www.wikidata.org/wiki/Q1757673","display_name":"Sobel operator","level":5,"score":0.701339066028595},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6751300692558289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6675133109092712},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5699257850646973},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5178449749946594},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5158683657646179},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.49455997347831726},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4443759322166443},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.44059643149375916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43650615215301514},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.42688918113708496},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.4225963354110718},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4194572865962982},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3831520676612854},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.35531359910964966},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2013091742992401},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10482534766197205},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr.2004.1334156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2004.1334156","pdf_url":null,"source":{"id":"https://openalex.org/S4363608750","display_name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1972774730","https://openalex.org/W2014411734","https://openalex.org/W2090874155","https://openalex.org/W2101135801","https://openalex.org/W2146620674","https://openalex.org/W2164434191","https://openalex.org/W6675319681","https://openalex.org/W6684331871"],"related_works":["https://openalex.org/W4388400392","https://openalex.org/W2383455043","https://openalex.org/W2343079405","https://openalex.org/W2269083758","https://openalex.org/W1974517722","https://openalex.org/W2367735169","https://openalex.org/W2545393398","https://openalex.org/W4225576506","https://openalex.org/W3134757346","https://openalex.org/W2378692644"],"abstract_inverted_index":{"Captions":[0],"in":[1,8],"videos":[2],"often":[3],"play":[4],"an":[5],"important":[6],"role":[7],"video":[9,21],"information":[10],"indexing":[11],"and":[12,54,83,114,135],"retrieval.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17,105],"present":[18,106],"a":[19,28,55,74,96,107],"novel":[20],"caption":[22],"detection":[23,70],"approach.":[24],"We":[25,94],"first":[26],"apply":[27],"new":[29,108],"multiple":[30],"frame":[31],"integration":[32],"(MFI)":[33],"method":[34,113],"to":[35,61,79,99],"minimize":[36],"variation":[37],"of":[38,41,65],"the":[39,42,63,81,129],"background":[40],"image.":[43],"A":[44],"time-based":[45],"minimum":[46],"(or":[47],"maximum)":[48],"pixel":[49],"value":[50],"search":[51],"is":[52,59,71,77],"employed":[53],"Sobel":[56,90],"edge":[57],"map":[58],"used":[60,78],"determine":[62],"mode":[64],"search.":[66],"Then":[67],"block-based":[68],"text":[69,86,102,110,116,123],"performed,":[72],"i.e.,":[73],"small":[75],"window":[76],"scan":[80],"image":[82],"classify":[84],"as":[85,92],"or":[87],"non-text,":[88],"using":[89],"edges":[91],"features.":[93],"use":[95],"two-level":[97],"pyramid":[98],"detect":[100],"various":[101],"sizes.":[103],"Finally,":[104],"iterative":[109],"line":[111],"decomposition":[112],"accurate":[115],"bounding":[117],"boxes":[118],"are":[119],"extracted":[120],"from":[121],"candidate":[122],"areas.":[124],"Experimental":[125],"result":[126],"shows":[127],"that":[128],"proposed":[130],"approach":[131],"achieves":[132],"high":[133],"precision":[134],"recall.":[136]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}