{"id":"https://openalex.org/W2955802371","doi":"https://doi.org/10.1145/3330393.3330410","title":"An Improved Approach Based on CNN-RNNs for Mathematical Expression Recognition","display_name":"An Improved Approach Based on CNN-RNNs for Mathematical Expression Recognition","publication_year":2019,"publication_date":"2019-05-10","ids":{"openalex":"https://openalex.org/W2955802371","doi":"https://doi.org/10.1145/3330393.3330410","mag":"2955802371"},"language":"en","primary_location":{"id":"doi:10.1145/3330393.3330410","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330393.3330410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 4th International Conference on Multimedia Systems and Signal Processing","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/A5100756628","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0001-5556-3896"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102382946","display_name":"Zhiqiang Bai","orcid":"https://orcid.org/0000-0001-9793-3752"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Bai","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056706680","display_name":"Yuesheng Zhu","orcid":"https://orcid.org/0000-0003-2524-6800"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuesheng Zhu","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100756628"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.5183,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.86293208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9990000128746033,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9979000091552734,"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":0.7847148180007935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7342976331710815},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6573070883750916},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6352774500846863},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5417987704277039},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.540521502494812},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.526596188545227},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5138066411018372},{"id":"https://openalex.org/keywords/symbol","display_name":"Symbol (formal)","score":0.46901196241378784},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4524662494659424},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4317636489868164},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.41211211681365967},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3706517517566681},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34252941608428955},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24231436848640442},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.099924236536026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7847148180007935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7342976331710815},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6573070883750916},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6352774500846863},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5417987704277039},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.540521502494812},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.526596188545227},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5138066411018372},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.46901196241378784},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4524662494659424},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4317636489868164},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.41211211681365967},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3706517517566681},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34252941608428955},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24231436848640442},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.099924236536026},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3330393.3330410","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330393.3330410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 4th International Conference on Multimedia Systems and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1806891645","https://openalex.org/W1905882502","https://openalex.org/W1981451828","https://openalex.org/W2049035241","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2134557905","https://openalex.org/W2139186315","https://openalex.org/W2149167588","https://openalex.org/W2193413348","https://openalex.org/W2404394533","https://openalex.org/W2575842049","https://openalex.org/W2579854910","https://openalex.org/W2626154462","https://openalex.org/W2626778328","https://openalex.org/W2737725206","https://openalex.org/W2745461083","https://openalex.org/W2773656636","https://openalex.org/W2783219727","https://openalex.org/W2785641051","https://openalex.org/W2791148095","https://openalex.org/W2963311793","https://openalex.org/W2963637207","https://openalex.org/W2964018924","https://openalex.org/W2964108850","https://openalex.org/W2964189376","https://openalex.org/W4322695928","https://openalex.org/W6679806934","https://openalex.org/W6687566353","https://openalex.org/W6739447310","https://openalex.org/W6739901393","https://openalex.org/W6740017710"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W2922073769","https://openalex.org/W4378510483","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4221142204","https://openalex.org/W1492295194"],"abstract_inverted_index":{"Mathematical":[0],"expression":[1,90,101],"recognition":[2,14,20,28,79],"(MER)":[3],"in":[4,25,49,92],"images":[5,94,127,134],"is":[6,34,69,165,192,195],"a":[7,140,162],"challenging":[8],"task":[9],"due":[10],"to":[11,38,71,106,159,167],"formula":[12,42,77],"symbol":[13,78,121,151],"and":[15,29,44,80,97,117,128,146,182],"structured":[16],"analysis.":[17],"Optical":[18],"character":[19],"(OCR)":[21],"has":[22],"been":[23],"used":[24],"natural":[26],"language":[27],"many":[30],"areas.":[31],"However,":[32],"it":[33],"difficult":[35],"for":[36,75],"OCR":[37],"recognize":[39],"some":[40],"special":[41],"symbols":[43],"accurately":[45],"confirm":[46],"their":[47],"positions":[48],"MER.":[50],"In":[51,82,104,157],"this":[52],"paper,":[53],"an":[54,119],"improved":[55],"end-to-end":[56],"MER":[57,173],"approach":[58],"based":[59],"on":[60,179],"CNN-RNNs":[61],"(convolutional":[62],"neural":[63,67],"network":[64],"-":[65],"recurrent":[66],"networks)":[68],"proposed":[70,84],"optimize":[72],"the":[73,76,88,93,99,108,125,144,150,169,172,177,184],"processing":[74],"localization.":[81],"our":[83],"approach,":[85],"we":[86,123,138],"extract":[87,129],"mathematical":[89,100],"features":[91,131],"by":[95,102,135],"CNN":[96],"generate":[98],"RNNs.":[103],"order":[105],"improve":[107,168],"acquisition":[109],"of":[110,171,190],"fuzzy":[111],"or":[112],"small":[113],"symbolic":[114],"feature":[115],"information":[116],"get":[118],"accurate":[120],"position,":[122],"double":[124],"source":[126],"image":[130],"with":[132],"preprocessed":[133],"CNN.":[136],"And":[137],"add":[139],"double-attention":[141],"mechanism":[142],"between":[143],"encoder":[145],"decoder":[147],"so":[148],"that":[149],"position":[152],"can":[153],"be":[154],"obtained":[155],"accurately.":[156],"addition,":[158],"prevent":[160],"overfitting,":[161],"dropout":[163],"layer":[164],"introduced":[166],"generalization":[170],"model.":[174],"We":[175],"do":[176],"experiment":[178],"IM2LATEX-100K":[180],"dataset":[181],"obtain":[183],"comparative":[185],"result.":[186],"A":[187],"BLEU":[188],"accuracy":[189],"88.42%":[191],"achieved,":[193],"which":[194],"better":[196],"than":[197],"other":[198],"methods.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}