{"id":"https://openalex.org/W2770219248","doi":"https://doi.org/10.1109/globalsip.2017.8309070","title":"Efficient segmentation-aided text detection for intelligent robots","display_name":"Efficient segmentation-aided text detection for intelligent robots","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2770219248","doi":"https://doi.org/10.1109/globalsip.2017.8309070","mag":"2770219248"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip.2017.8309070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2017.8309070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","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/A5100723093","display_name":"Junting Zhang","orcid":"https://orcid.org/0000-0002-0019-6803"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Junting Zhang","raw_affiliation_strings":["University of Southern California, Los Angeles, CA 90089, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022245400","display_name":"Yuewei Na","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuewei Na","raw_affiliation_strings":["University of Southern California, Los Angeles, CA 90089, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100615754","display_name":"Siyang Li","orcid":"https://orcid.org/0000-0002-5991-649X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyang Li","raw_affiliation_strings":["University of Southern California, Los Angeles, CA 90089, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001082656","display_name":"C.\u2010C. Jay Kuo","orcid":"https://orcid.org/0000-0001-9474-5035"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.-C. Jay Kuo","raw_affiliation_strings":["University of Southern California, Los Angeles, CA 90089, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100723093"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17019177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"798","last_page":"802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","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/T10601","display_name":"Handwritten Text Recognition Techniques","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8127765655517578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7600587606430054},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.682790219783783},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6643019318580627},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.6223465800285339},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5029494166374207},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.49726441502571106},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4757118821144104},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4631599187850952},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45577386021614075},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4377589523792267},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4210802912712097},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4194744825363159},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41050055623054504},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3615860044956207},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35706406831741333},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1783980429172516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8127765655517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7600587606430054},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.682790219783783},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6643019318580627},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.6223465800285339},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5029494166374207},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.49726441502571106},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4757118821144104},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4631599187850952},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45577386021614075},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4377589523792267},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4210802912712097},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4194744825363159},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41050055623054504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3615860044956207},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35706406831741333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1783980429172516},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globalsip.2017.8309070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2017.8309070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W117491841","https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W1922126009","https://openalex.org/W1935817682","https://openalex.org/W2008806374","https://openalex.org/W2061802763","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2131447359","https://openalex.org/W2142159465","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2239285313","https://openalex.org/W2253806798","https://openalex.org/W2271840356","https://openalex.org/W2333563142","https://openalex.org/W2339589954","https://openalex.org/W2412782625","https://openalex.org/W2464918637","https://openalex.org/W2519818067","https://openalex.org/W2550687635","https://openalex.org/W2579985080","https://openalex.org/W2607075434","https://openalex.org/W2613718673","https://openalex.org/W2962773189","https://openalex.org/W2963037989","https://openalex.org/W2964121744","https://openalex.org/W3106250896","https://openalex.org/W4295246343","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6631782140","https://openalex.org/W6639102338","https://openalex.org/W6689736890","https://openalex.org/W6691603626","https://openalex.org/W6729791593"],"related_works":["https://openalex.org/W3166204570","https://openalex.org/W3121246613","https://openalex.org/W2132137594","https://openalex.org/W2093537624","https://openalex.org/W350499458","https://openalex.org/W4321784794","https://openalex.org/W4283034653","https://openalex.org/W4387968066","https://openalex.org/W3104052051","https://openalex.org/W2187298888"],"abstract_inverted_index":{"Scene":[0],"text":[1,57,86],"detection":[2,58],"is":[3],"a":[4,29,37,80,104],"critical":[5],"prerequisite":[6],"for":[7,11,99],"many":[8],"fascinating":[9],"applications":[10],"vision-based":[12],"intelligent":[13],"robots.":[14],"Existing":[15],"methods":[16,126],"detect":[17],"texts":[18],"either":[19],"using":[20,66],"the":[21,62,76,85,92,96,100,112,121],"local":[22],"information":[23],"only":[24],"or":[25,43],"casting":[26],"it":[27],"as":[28],"semantic":[30],"segmentation":[31,81],"problem.":[32],"They":[33],"tend":[34],"to":[35,94],"produce":[36],"large":[38],"number":[39],"of":[40,79],"false":[41],"alarms":[42],"cannot":[44],"separate":[45],"individual":[46],"words":[47],"accurately.":[48],"In":[49],"this":[50],"work,":[51],"we":[52],"present":[53],"an":[54,67],"elegant":[55],"segmentation-aided":[56],"solution":[59],"that":[60,120],"predicts":[61],"word-level":[63],"bounding":[64],"boxes":[65],"end-to-end":[68],"trainable":[69],"deep":[70],"convolutional":[71,97],"neural":[72],"network.":[73],"It":[74],"exploits":[75],"holistic":[77],"view":[78],"network":[82],"in":[83],"generating":[84],"attention":[87],"map":[88],"(TAM)":[89],"and":[90,114,118],"uses":[91],"TAM":[93],"refine":[95],"features":[98],"MultiBox":[101],"detector":[102],"through":[103],"multiplicative":[105],"gating":[106],"process.":[107],"We":[108],"conduct":[109],"experiments":[110],"on":[111],"large-scale":[113],"challenging":[115],"COCO-Text":[116],"dataset":[117],"demonstrate":[119],"proposed":[122],"method":[123],"outperforms":[124],"state-of-the-art":[125],"significantly.":[127]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}