{"id":"https://openalex.org/W3198170507","doi":"https://doi.org/10.1145/3460426.3463612","title":"Reading Scene Text by Fusing Visual Attention with Semantic Representations","display_name":"Reading Scene Text by Fusing Visual Attention with Semantic Representations","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3198170507","doi":"https://doi.org/10.1145/3460426.3463612","mag":"3198170507"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3463612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","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/A5101564586","display_name":"Zhiguang Liu","orcid":"https://orcid.org/0000-0002-9011-5156"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiguang Liu","raw_affiliation_strings":["Noah's Ark Lab & Huawei Technologies, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Noah's Ark Lab & Huawei Technologies, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120218293","display_name":"Liangwei Wang","orcid":"https://orcid.org/0000-0001-5989-9338"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangwei Wang","raw_affiliation_strings":["Noah's Ark Lab & Huawei Technologies, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Noah's Ark Lab & Huawei Technologies, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010415169","display_name":"Jian Qiao","orcid":"https://orcid.org/0000-0002-5476-5135"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Qiao","raw_affiliation_strings":["Huawei Technologies, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101564586"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":0.0961,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39316993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"210","last_page":"218"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9925000071525574,"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":0.9923999905586243,"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":0.8282955288887024},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6865943670272827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6410647630691528},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5890796184539795},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5069918632507324},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.465654194355011},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4528745412826538},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42548587918281555},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0956771969795227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8282955288887024},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6865943670272827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6410647630691528},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5890796184539795},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5069918632507324},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.465654194355011},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4528745412826538},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42548587918281555},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0956771969795227},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460426.3463612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8700000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1491389626","https://openalex.org/W1971822075","https://openalex.org/W1978729128","https://openalex.org/W2078446911","https://openalex.org/W2194187530","https://openalex.org/W2294053032","https://openalex.org/W2343052201","https://openalex.org/W2531563875","https://openalex.org/W2750938222","https://openalex.org/W2788069964","https://openalex.org/W2788840914","https://openalex.org/W2795619303","https://openalex.org/W2810983211","https://openalex.org/W2896034938","https://openalex.org/W2963233387","https://openalex.org/W2963327605","https://openalex.org/W2963403868","https://openalex.org/W2963517393","https://openalex.org/W2963526661","https://openalex.org/W2963909453","https://openalex.org/W2964296749","https://openalex.org/W2997749585","https://openalex.org/W2998382406","https://openalex.org/W3043311956","https://openalex.org/W3106271744"],"related_works":["https://openalex.org/W2081647779","https://openalex.org/W3185852197","https://openalex.org/W1529136209","https://openalex.org/W1987157392","https://openalex.org/W4293811952","https://openalex.org/W1539050421","https://openalex.org/W4288350158","https://openalex.org/W2946205552","https://openalex.org/W2122691642","https://openalex.org/W2752697875"],"abstract_inverted_index":{"Recognizing":[0],"text":[1,54],"in":[2,10],"an":[3,105],"unconstrained":[4],"environment":[5],"is":[6,24,104],"a":[7,19,45,63,85,92],"challenging":[8],"task":[9],"computer":[11],"vision.":[12],"Many":[13],"prevalent":[14],"approaches":[15],"to":[16,26,40,49,67],"it":[17],"employ":[18],"recurrent":[20],"neural":[21],"network":[22],"that":[23,76,113,122],"difficult":[25],"train":[27],"or":[28],"rely":[29],"heavily":[30],"on":[31,128,143],"sophisticated":[32],"model":[33,94,103],"designs":[34],"for":[35],"sequence":[36,79],"modeling.":[37],"In":[38],"contrast":[39],"these":[41],"methods,":[42],"we":[43,87],"propose":[44],"unified":[46],"lexicon-free":[47],"framework":[48],"enhance":[50],"the":[51,77,81,96],"accuracy":[52],"of":[53,107,119,130],"recognition":[55,141],"using":[56],"only":[57],"attention":[58,65,102],"and":[59,71,110,134],"convolution.":[60],"We":[61],"use":[62],"relational":[64],"module":[66],"leverage":[68],"visual":[69,108],"patterns":[70],"word":[72],"representations.":[73],"To":[74],"ensure":[75],"predicted":[78],"captures":[80],"contextual":[82],"dependencies":[83,90],"within":[84],"word,":[86],"embed":[88],"linguistic":[89,111],"from":[91,132],"language":[93],"into":[95],"optimization":[97],"framework.":[98],"The":[99,117],"proposed":[100],"mutual":[101],"ensemble":[106],"cues":[109],"contexts":[112],"together":[114],"improve":[115],"performance.":[116],"results":[118],"experiments":[120],"show":[121],"our":[123],"system":[124],"achieves":[125],"state-of-the-art":[126],"performance":[127,142],"datasets":[129],"texts":[131],"regular":[133],"irregular":[135],"scenes.":[136],"It":[137],"also":[138],"significantly":[139],"enhances":[140],"noisy":[144],"scanned":[145],"documents.":[146]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}