{"id":"https://openalex.org/W4392904618","doi":"https://doi.org/10.1109/icassp48485.2024.10447346","title":"Viewing Writing as Video: Optical Flow based Multi-Modal Handwritten Mathematical Expression Recognition","display_name":"Viewing Writing as Video: Optical Flow based Multi-Modal Handwritten Mathematical Expression Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904618","doi":"https://doi.org/10.1109/icassp48485.2024.10447346"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447346","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101287529","display_name":"Hanbo Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanbo Cheng","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703619","display_name":"Pengfei Hu","orcid":"https://orcid.org/0000-0002-7935-886X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Hu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006572116","display_name":"Jiefeng Ma","orcid":"https://orcid.org/0000-0003-2416-3720"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiefeng Ma","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012060181","display_name":"Zhenrong Zhang","orcid":"https://orcid.org/0000-0003-1125-6637"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenrong Zhang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002149153","display_name":"Mobai Xue","orcid":"https://orcid.org/0000-0002-8315-9492"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mobai Xue","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"5695","last_page":"5699"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9973000288009644,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9973000288009644,"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":0.9973000288009644,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.848662793636322},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7214468121528625},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.6752796173095703},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6321967840194702},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.554252028465271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5426798462867737},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5283749103546143},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5165414214134216},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5004310607910156},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49915027618408203},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.46590691804885864},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4577944874763489},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3810023069381714},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34200775623321533},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3360733389854431},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.320160448551178},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.26014214754104614},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08626115322113037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.848662793636322},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7214468121528625},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.6752796173095703},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6321967840194702},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.554252028465271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5426798462867737},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5283749103546143},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5165414214134216},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5004310607910156},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49915027618408203},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.46590691804885864},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4577944874763489},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3810023069381714},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34200775623321533},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3360733389854431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.320160448551178},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26014214754104614},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08626115322113037},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447346","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1583837637","https://openalex.org/W1924770834","https://openalex.org/W2133564696","https://openalex.org/W2507009361","https://openalex.org/W2623860192","https://openalex.org/W2806717845","https://openalex.org/W2914304175","https://openalex.org/W2963446712","https://openalex.org/W2963637207","https://openalex.org/W2964108850","https://openalex.org/W3004194266","https://openalex.org/W3004196288","https://openalex.org/W3110190397","https://openalex.org/W3164707697","https://openalex.org/W3176268775","https://openalex.org/W3198658540","https://openalex.org/W3201757274","https://openalex.org/W4200635795","https://openalex.org/W4283803766","https://openalex.org/W4312299669","https://openalex.org/W4312868947","https://openalex.org/W4313125865","https://openalex.org/W4360595157","https://openalex.org/W4372342075","https://openalex.org/W4376653374","https://openalex.org/W4385151419","https://openalex.org/W6640212811","https://openalex.org/W6679434410","https://openalex.org/W6682864246","https://openalex.org/W6725739302","https://openalex.org/W6779107661","https://openalex.org/W6852609638"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Handwritten":[0],"Mathematical":[1],"Expression":[2],"Recognition":[3],"(HMER)":[4],"forms":[5],"a":[6,44,50,55,87],"crucial":[7],"task":[8],"in":[9,73,119,164],"the":[10,23,58,62,83,91,99,107,113,127],"domain":[11],"of":[12,57],"document":[13],"intelligence.":[14],"It":[15,32],"encompasses":[16],"online":[17,38,63,100,130],"and":[18,26,39,64,76,89,125,131,152,159],"offline":[19,40,65,108,132,146],"modalities,":[20,66],"which":[21,67,102],"utilize":[22,36],"trajectory":[24],"sequence":[25],"static":[27],"image":[28],"as":[29,54,86],"input,":[30],"respectively.":[31],"is":[33,103,167],"intuitive":[34],"to":[35,42,70,97,121,143],"both":[37],"modalities":[41],"build":[43],"more":[45,104],"powerful":[46],"recognition":[47],"system.":[48],"However,":[49],"formidable":[51],"challenge":[52],"arises":[53],"result":[56],"substantial":[59,153],"heterogeneity":[60],"between":[61],"consequently":[68],"leads":[69],"considerable":[71],"obstacles":[72],"their":[74],"alignment":[75],"fusion.":[77],"In":[78],"this":[79,165],"work,":[80],"we":[81,111],"perceive":[82],"writing":[84],"process":[85],"video":[88],"introduce":[90],"Aggregated":[92],"Optical":[93,114],"Flow":[94,115],"Map":[95],"(AOFM)":[96],"represent":[98],"modality,":[101],"compatible":[105],"with":[106],"modality.":[109],"Additionally,":[110],"propose":[112],"Aware":[116],"Network":[117],"(OFAN)":[118],"order":[120],"automatically":[122],"extract,":[123],"align,":[124],"fuse":[126],"features":[128],"across":[129,155],"modalities.":[133],"Through":[134],"experiment":[135],"analysis,":[136],"our":[137],"method":[138],"can":[139],"be":[140],"seamlessly":[141],"applied":[142],"multiple":[144],"existing":[145],"HMER":[147],"models,":[148],"thereby":[149],"yielding":[150],"stable":[151],"enhancements":[154],"CROHME":[156],"2014,":[157],"2016,":[158],"2019":[160],"datasets.":[161],"The":[162],"code":[163],"work":[166],"available":[168],"at":[169],"https:":[170],"//github.com/Hanbo-Cheng/OFAN.git.":[171]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
