{"id":"https://openalex.org/W3196836367","doi":"https://doi.org/10.1142/s0218001421600090","title":"A New Hybrid Method for Caption and Scene Text Classification in Action Video Images","display_name":"A New Hybrid Method for Caption and Scene Text Classification in Action Video Images","publication_year":2021,"publication_date":"2021-09-06","ids":{"openalex":"https://openalex.org/W3196836367","doi":"https://doi.org/10.1142/s0218001421600090","mag":"3196836367"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001421600090","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001421600090","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-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/A5033782598","display_name":"Lokesh Nandanwar","orcid":"https://orcid.org/0000-0001-7201-0855"},"institutions":[{"id":"https://openalex.org/I33849332","display_name":"University of Malaya","ror":"https://ror.org/00rzspn62","country_code":"MY","type":"education","lineage":["https://openalex.org/I33849332"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Lokesh Nandanwar","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur, Malaysia","institution_ids":["https://openalex.org/I33849332"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025871978","display_name":"Palaiahnakote Shivakumara","orcid":"https://orcid.org/0000-0001-9026-4613"},"institutions":[{"id":"https://openalex.org/I33849332","display_name":"University of Malaya","ror":"https://ror.org/00rzspn62","country_code":"MY","type":"education","lineage":["https://openalex.org/I33849332"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Palaiahnakote Shivakumara","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur, Malaysia","institution_ids":["https://openalex.org/I33849332"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068803496","display_name":"Umapada Pal","orcid":"https://orcid.org/0000-0002-5426-2618"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Umapada Pal","raw_affiliation_strings":["Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061696740","display_name":"Tong L\u00fc","orcid":"https://orcid.org/0000-0002-7051-5347"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Lu","raw_affiliation_strings":["National Key Lab for Novel Software Technology, Nanjing University, Nanjing, P. R. China"],"affiliations":[{"raw_affiliation_string":"National Key Lab for Novel Software Technology, Nanjing University, Nanjing, P. R. China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045600512","display_name":"Michael Blumenstein","orcid":"https://orcid.org/0000-0002-9908-3744"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Michael Blumenstein","raw_affiliation_strings":["University of Technology Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025871978"],"corresponding_institution_ids":["https://openalex.org/I33849332"],"apc_list":null,"apc_paid":null,"fwci":0.2882,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55663399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"35","issue":"12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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/T11439","display_name":"Video Analysis and Summarization","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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9983000159263611,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7689018249511719},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7608025074005127},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.6111789345741272},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5642656683921814},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5570569038391113},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5195460915565491},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.48392730951309204},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.48220813274383545},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.46823635697364807},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44848594069480896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16522198915481567}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7689018249511719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608025074005127},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.6111789345741272},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5642656683921814},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5570569038391113},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5195460915565491},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.48392730951309204},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48220813274383545},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.46823635697364807},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44848594069480896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16522198915481567},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001421600090","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001421600090","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1493331862","https://openalex.org/W2041004593","https://openalex.org/W2069162951","https://openalex.org/W2251806676","https://openalex.org/W2303099520","https://openalex.org/W2421016805","https://openalex.org/W2439424429","https://openalex.org/W2576995890","https://openalex.org/W2596162275","https://openalex.org/W2733137411","https://openalex.org/W2769581371","https://openalex.org/W2786732739","https://openalex.org/W2787265885","https://openalex.org/W2790969304","https://openalex.org/W2810983211","https://openalex.org/W2963526661","https://openalex.org/W2964054038","https://openalex.org/W2984242461","https://openalex.org/W3091795713"],"related_works":["https://openalex.org/W2055682261","https://openalex.org/W1916685473","https://openalex.org/W1993363272","https://openalex.org/W2186390138","https://openalex.org/W2790129917","https://openalex.org/W2060035984","https://openalex.org/W2992856432","https://openalex.org/W2100638064","https://openalex.org/W2174937762","https://openalex.org/W2212883587"],"abstract_inverted_index":{"Achieving":[0],"a":[1,30,48,79,91,161,183,201],"better":[2],"recognition":[3,218,234],"rate":[4],"for":[5,33,109,121,167,189],"text":[6,18,44,77],"in":[7,22,53,82,144],"action":[8,60,198],"video":[9,54,85],"images":[10,108,174],"is":[11,39,47,71,213],"challenging":[12],"due":[13],"to":[14,104,159,182,241],"multiple":[15],"types":[16,75],"of":[17,36,50,76,123,126,152,191,220],"with":[19,176,204],"unpredictable":[20],"actions":[21],"the":[23,34,51,84,106,119,132,138,149,157,169,177,205,210,217,221,225,233],"background.":[24],"In":[25,215],"this":[26],"paper,":[27],"we":[28,164],"propose":[29],"new":[31,92],"method":[32,89,212],"classification":[35,190,226],"caption":[37,110],"(which":[38],"edited":[40],"text)":[41],"and":[42,67,101,111,128,131,200,223],"scene":[43,112],"(text":[45],"that":[46,73,155,209,232],"part":[49],"video)":[52],"images.":[55],"This":[56,141],"work":[57],"considers":[58],"five":[59,197],"classes,":[61],"namely,":[62],"Yoga,":[63],"Concert,":[64],"Teleshopping,":[65],"Craft,":[66],"Recipes,":[68],"where":[69],"it":[70],"expected":[72],"both":[74],"play":[78],"vital":[80],"role":[81],"understanding":[83],"content.":[86],"The":[87,114,172],"proposed":[88,211],"introduces":[90],"fusion":[93,115],"criterion":[94,116],"based":[95],"on":[96,196],"Discrete":[97],"Cosine":[98],"Transform":[99],"(DCT)":[100],"Fourier":[102,129],"coefficients":[103,122],"obtain":[105],"reconstructed":[107,173],"text.":[113,193],"involves":[117],"computing":[118],"variances":[120,134],"corresponding":[124],"pixels":[125],"DCT":[127],"images,":[130],"same":[133],"are":[135,180],"considered":[136],"as":[137],"respective":[139],"weights.":[140],"step":[142],"results":[143,195,219],"Reconstructed":[145,170],"image-1.":[146],"Inspired":[147],"by":[148],"special":[150],"property":[151],"Chebyshev-Harmonic-Fourier-Moments":[153],"(CHFM)":[154],"has":[156],"ability":[158],"reconstruct":[160],"redundancy-free":[162],"image,":[163],"explore":[165],"CHFM":[166],"obtaining":[168],"image-2.":[171],"along":[175],"input":[178],"image":[179],"passed":[181],"Deep":[184],"Convolutional":[185],"Neural":[186],"Network":[187],"(DCNN)":[188],"caption/scene":[192],"Experimental":[194],"classes":[199],"comparative":[202],"study":[203],"existing":[206],"methods":[207,230],"demonstrate":[208],"effective.":[214],"addition,":[216],"before":[222,242],"after":[224,238],"obtained":[227],"from":[228],"different":[229],"show":[231],"performance":[235],"improves":[236],"significantly":[237],"classification,":[239],"compared":[240],"classification.":[243]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}