{"id":"https://openalex.org/W4372263458","doi":"https://doi.org/10.1109/icassp49357.2023.10096676","title":"Mask Guided Selective Context Decoding for Handwritten Chinese Text Recognition","display_name":"Mask Guided Selective Context Decoding for Handwritten Chinese Text Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372263458","doi":"https://doi.org/10.1109/icassp49357.2023.10096676"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100455358","display_name":"Tao Li","orcid":"https://orcid.org/0000-0002-9724-3812"},"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":"Tao Li","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057201752","display_name":"Shilian Wu","orcid":"https://orcid.org/0000-0003-1263-4652"},"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":"Shilian Wu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103123751","display_name":"Zengfu Wang","orcid":"https://orcid.org/0000-0003-1859-900X"},"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":"Zengfu Wang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of 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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9950000047683716,"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":0.9916999936103821,"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":0.7915420532226562},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7208133339881897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5966631174087524},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5421593189239502},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5287284851074219},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5149899125099182},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48157787322998047},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4610530436038971},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.452130526304245},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3669632077217102},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3434094786643982},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32546424865722656},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31203746795654297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915420532226562},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7208133339881897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5966631174087524},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5421593189239502},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5287284851074219},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5149899125099182},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48157787322998047},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4610530436038971},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.452130526304245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3669632077217102},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434094786643982},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32546424865722656},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31203746795654297},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1647671624","https://openalex.org/W1978964824","https://openalex.org/W2004767896","https://openalex.org/W2033404582","https://openalex.org/W2119305530","https://openalex.org/W2156338447","https://openalex.org/W2194187530","https://openalex.org/W2578496721","https://openalex.org/W2808523546","https://openalex.org/W2970597249","https://openalex.org/W2979371747","https://openalex.org/W2987258871","https://openalex.org/W3004264980","https://openalex.org/W3004388780","https://openalex.org/W3045717997","https://openalex.org/W3049336660","https://openalex.org/W3108417399","https://openalex.org/W3197469504","https://openalex.org/W3202415716","https://openalex.org/W4210337376","https://openalex.org/W4312879041","https://openalex.org/W6623517193","https://openalex.org/W6636915900","https://openalex.org/W6760749843","https://openalex.org/W6763701032","https://openalex.org/W6807342097"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W350032239","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W2073435713"],"abstract_inverted_index":{"Handwritten":[0],"Chinese":[1],"text":[2],"recognition":[3],"(HCTR)":[4],"is":[5,59,90],"challenging":[6],"due":[7,61],"to":[8,38,62,92,96],"its":[9,31,63],"thousand":[10],"of":[11,55,79],"characters,":[12],"diverse":[13],"writing":[14],"styles,":[15],"and":[16,81],"ambiguous":[17],"segmentation.":[18],"Currently,":[19],"methods":[20,47],"based":[21,46],"on":[22],"connectionist":[23],"temporal":[24],"classification":[25],"(CTC)":[26],"are":[27],"widely":[28],"used,":[29],"while":[30],"independent":[32],"decoding":[33,66],"nature":[34],"makes":[35],"it":[36],"unable":[37],"leverage":[39],"contextual":[40,50,57],"information":[41,58],"effectively.":[42],"In":[43],"contrast,":[44],"auto-regression":[45],"benefit":[48],"from":[49],"reasoning,":[51],"but":[52],"only":[53],"half":[54],"the":[56,94,105,113],"utilized":[60],"inherent":[64],"unidirectionally":[65],"nature.":[67],"This":[68],"article":[69],"proposes":[70],"a":[71,85],"multi-modal":[72],"attention-based":[73],"framework":[74],"for":[75],"offline":[76],"HCTR":[77],"capable":[78],"visual":[80],"semantic":[82,106],"reasoning.":[83],"Moreover,":[84],"novel":[86],"mask-guided":[87],"context-selective":[88],"decoder":[89],"presented":[91],"guide":[93],"network":[95],"decode":[97],"with":[98],"randomly":[99],"selected":[100],"bidirectional":[101],"context,":[102],"further":[103],"improving":[104],"reasoning":[107],"ability.":[108],"Extensive":[109],"experiments":[110],"show":[111],"that":[112],"proposed":[114],"method":[115],"significantly":[116],"outperforms":[117],"previous":[118],"methods.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}