{"id":"https://openalex.org/W2145020494","doi":"https://doi.org/10.1109/tmm.2011.2177646","title":"Robustly Extracting Captions in Videos Based on Stroke-Like Edges and Spatio-Temporal Analysis","display_name":"Robustly Extracting Captions in Videos Based on Stroke-Like Edges and Spatio-Temporal Analysis","publication_year":2011,"publication_date":"2011-12-02","ids":{"openalex":"https://openalex.org/W2145020494","doi":"https://doi.org/10.1109/tmm.2011.2177646","mag":"2145020494"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2011.2177646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2011.2177646","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5100683612","display_name":"Xiaoqian Liu","orcid":"https://orcid.org/0000-0002-2187-8598"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqian Liu","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","Grad. Univ. of Chinese Acad. of Sci., Beijing, , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Grad. Univ. of Chinese Acad. of Sci., Beijing, , China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109203493","display_name":"Weiqiang Wang","orcid":"https://orcid.org/0000-0002-0004-7154"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqiang Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","Key Lab. of Intell. Inf. Process., Inst. of Comput. Technol., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Key Lab. of Intell. Inf. Process., Inst. of Comput. Technol., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9188,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.8844907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"14","issue":"2","first_page":"482","last_page":"489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991000294685364,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991000294685364,"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":0.9987000226974487,"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":0.9980000257492065,"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":0.8690450191497803},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8027732372283936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7435511350631714},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6707125306129456},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6524974703788757},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6018152236938477},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5176730155944824},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5157699584960938},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48553013801574707},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42967918515205383},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4184381365776062},{"id":"https://openalex.org/keywords/edge-detection","display_name":"Edge detection","score":0.4108458459377289},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3528844714164734},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.26281416416168213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8690450191497803},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8027732372283936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7435511350631714},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6707125306129456},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6524974703788757},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6018152236938477},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5176730155944824},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5157699584960938},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48553013801574707},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42967918515205383},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4184381365776062},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.4108458459377289},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3528844714164734},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26281416416168213},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2011.2177646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2011.2177646","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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":30,"referenced_works":["https://openalex.org/W1501002325","https://openalex.org/W1539258218","https://openalex.org/W1599061990","https://openalex.org/W1852672725","https://openalex.org/W1989960151","https://openalex.org/W1990179043","https://openalex.org/W2006251269","https://openalex.org/W2014411734","https://openalex.org/W2019273017","https://openalex.org/W2020935547","https://openalex.org/W2027883219","https://openalex.org/W2033961077","https://openalex.org/W2071267894","https://openalex.org/W2119200665","https://openalex.org/W2120980417","https://openalex.org/W2124164882","https://openalex.org/W2130103520","https://openalex.org/W2131093082","https://openalex.org/W2137718414","https://openalex.org/W2142082467","https://openalex.org/W2142159465","https://openalex.org/W2143127796","https://openalex.org/W2146073616","https://openalex.org/W2158878654","https://openalex.org/W2166274584","https://openalex.org/W2555860637","https://openalex.org/W6632178270","https://openalex.org/W6638800456","https://openalex.org/W6678330061","https://openalex.org/W6679388247"],"related_works":["https://openalex.org/W1986338341","https://openalex.org/W2389546251","https://openalex.org/W2369556382","https://openalex.org/W1994279415","https://openalex.org/W2545205567","https://openalex.org/W2358253773","https://openalex.org/W2367019649","https://openalex.org/W2116510815","https://openalex.org/W17460865","https://openalex.org/W2372578044"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,89],"effective":[4],"and":[5,54,111,129,149],"efficient":[6],"approach":[7,63],"to":[8,50],"extracting":[9],"captions":[10,57],"from":[11,19],"videos.":[12],"The":[13],"robustness":[14,148],"of":[15,22,42,56,67,76,83,98,107,118,126,151],"our":[16,62,135,152],"system":[17],"comes":[18],"two":[20,142],"aspects":[21],"contributions.":[23],"First,":[24],"we":[25,113],"propose":[26],"a":[27],"novel":[28],"stroke-like":[29],"edge":[30],"detection":[31,53],"method":[32],"based":[33],"on":[34,141],"contours,":[35],"which":[36],"can":[37,121],"effectively":[38,122],"remove":[39],"the":[40,52,65,74,95,105,116,124,133,138,147],"interference":[41],"non-stroke":[43],"edges":[44],"in":[45,73,104],"complex":[46],"background":[47],"so":[48],"as":[49,88],"make":[51],"localization":[55,128],"much":[58],"more":[59],"accurate.":[60],"Second,":[61],"highlights":[64],"importance":[66],"temporal":[68,96],"feature,":[69,72],"i.e.,":[70],"inter-frame":[71,119],"task":[75],"caption":[77,108,127,130],"extraction":[78],"(detection,":[79],"localization,":[80,109],"segmentation).":[81],"Instead":[82],"regarding":[84],"each":[85],"video":[86,99],"frame":[87],"independent":[90],"image,":[91],"through":[92],"fully":[93],"utilizing":[94],"feature":[97],"together":[100],"with":[101],"spatial":[102],"analysis":[103],"computation":[106],"segmentation":[110],"post-processing,":[112],"demonstrate":[114],"that":[115],"use":[117],"information":[120],"improve":[123],"accuracy":[125],"segmentation.":[131],"In":[132],"comprehensive":[134],"evaluation":[136],"experiments,":[137],"experimental":[139],"results":[140],"representative":[143],"datasets":[144],"have":[145],"shown":[146],"efficiency":[150],"approach.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}