{"id":"https://openalex.org/W2131093082","doi":"https://doi.org/10.1109/tnn.2002.1021896","title":"A spatial-temporal approach for video caption detection and recognition","display_name":"A spatial-temporal approach for video caption detection and recognition","publication_year":2002,"publication_date":"2002-07-01","ids":{"openalex":"https://openalex.org/W2131093082","doi":"https://doi.org/10.1109/tnn.2002.1021896","mag":"2131093082","pmid":"https://pubmed.ncbi.nlm.nih.gov/18244491"},"language":"en","primary_location":{"id":"doi:10.1109/tnn.2002.1021896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnn.2002.1021896","pdf_url":null,"source":{"id":"https://openalex.org/S42080949","display_name":"IEEE Transactions on Neural Networks","issn_l":"1045-9227","issn":["1045-9227","1941-0093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/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":true,"raw_author_name":"Xiaoou Tang","raw_affiliation_strings":["Dept. of Inf. Eng., Chinese Univ. of Hong Kong, China","Dept. of Information Engineering, Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Inf. Eng., Chinese Univ. of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Information Engineering, Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785348","display_name":"Xinbo Gao","orcid":"https://orcid.org/0000-0003-1443-0776"},"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":"Xinbo Gao","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong, China","Dept. of Information Engineering, Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Information Engineering, Chinese University of 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, Hong Kong, China","Dept. of Information Engineering, Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Information Engineering, Chinese University of 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","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"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/A5110380387"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":3.4881,"has_fulltext":false,"cited_by_count":130,"citation_normalized_percentile":{"value":0.93801381,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"13","issue":"4","first_page":"961","last_page":"971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9901000261306763,"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":0.8268841505050659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7512646913528442},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5403199195861816},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.537566065788269},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5311649441719055},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5177754163742065},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4679167568683624},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45175209641456604},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43412554264068604},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.42348945140838623},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3268108665943146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8268841505050659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7512646913528442},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5403199195861816},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.537566065788269},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5311649441719055},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5177754163742065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4679167568683624},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45175209641456604},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43412554264068604},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.42348945140838623},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3268108665943146}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnn.2002.1021896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnn.2002.1021896","pdf_url":null,"source":{"id":"https://openalex.org/S42080949","display_name":"IEEE Transactions on Neural Networks","issn_l":"1045-9227","issn":["1045-9227","1941-0093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks","raw_type":"journal-article"},{"id":"pmid:18244491","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18244491","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.6131","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.6131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mmlab.ie.cuhk.edu.hk/2002/NN02_Video.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1225789377","https://openalex.org/W1480779007","https://openalex.org/W1501691825","https://openalex.org/W1590178533","https://openalex.org/W1776985898","https://openalex.org/W1852672725","https://openalex.org/W1891152514","https://openalex.org/W1900606880","https://openalex.org/W1962397371","https://openalex.org/W1963597005","https://openalex.org/W1972774730","https://openalex.org/W1977334762","https://openalex.org/W1977654659","https://openalex.org/W1986926502","https://openalex.org/W1987857333","https://openalex.org/W2003092111","https://openalex.org/W2005964041","https://openalex.org/W2006830243","https://openalex.org/W2010551968","https://openalex.org/W2012801633","https://openalex.org/W2019995264","https://openalex.org/W2049799721","https://openalex.org/W2063541573","https://openalex.org/W2077939625","https://openalex.org/W2090874155","https://openalex.org/W2096422142","https://openalex.org/W2102170122","https://openalex.org/W2111217344","https://openalex.org/W2112306108","https://openalex.org/W2117586922","https://openalex.org/W2120980417","https://openalex.org/W2121839820","https://openalex.org/W2125693015","https://openalex.org/W2133377862","https://openalex.org/W2135346934","https://openalex.org/W2136941041","https://openalex.org/W2149032327","https://openalex.org/W2153313050","https://openalex.org/W2153624852","https://openalex.org/W2157709461","https://openalex.org/W2160069326","https://openalex.org/W2160700903","https://openalex.org/W6628154044","https://openalex.org/W6635216893","https://openalex.org/W6638180245","https://openalex.org/W6678818722","https://openalex.org/W7064073185"],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W2090259340","https://openalex.org/W4310225030","https://openalex.org/W2083665254","https://openalex.org/W2393816671","https://openalex.org/W1534720161","https://openalex.org/W2804957450","https://openalex.org/W1522196789"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,11,18,59],"video":[3,31,63],"caption":[4],"detection":[5,21],"and":[6,27,36,44],"recognition":[7,52],"system":[8],"based":[9],"on":[10,58,69],"fuzzy-clustering":[12],"neural":[13],"network":[14],"(FCNN)":[15],"classifier.":[16],"Using":[17],"novel":[19],"caption-transition":[20],"scheme":[22],"we":[23,47],"locate":[24],"both":[25],"spatial":[26],"temporal":[28],"positions":[29],"of":[30,61],"captions":[32],"with":[33],"high":[34],"precision":[35],"efficiency.":[37],"Then":[38],"employing":[39],"several":[40],"new":[41],"character":[42],"segmentation":[43],"binarization":[45],"techniques,":[46],"improve":[48],"the":[49,66],"Chinese":[50,70],"video-caption":[51,71],"accuracy":[53],"from":[54],"13%":[55],"to":[56],"86%":[57],"set":[60],"news":[62],"captions.":[64],"As":[65],"first":[67],"attempt":[68],"recognition,":[72],"our":[73],"experiment":[74],"results":[75],"are":[76],"very":[77],"encouraging.":[78]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}