{"id":"https://openalex.org/W4362564497","doi":"https://doi.org/10.1145/3577164.3577165","title":"Text Detection and Recognition in Natural Scenes Based on TWO-DIMENSIONAL Attention","display_name":"Text Detection and Recognition in Natural Scenes Based on TWO-DIMENSIONAL Attention","publication_year":2022,"publication_date":"2022-11-25","ids":{"openalex":"https://openalex.org/W4362564497","doi":"https://doi.org/10.1145/3577164.3577165"},"language":"en","primary_location":{"id":"doi:10.1145/3577164.3577165","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577164.3577165","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577164.3577165","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 4th International Conference on Video, Signal and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3577164.3577165","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087428737","display_name":"Baicun Guo","orcid":"https://orcid.org/0000-0002-2755-2687"},"institutions":[{"id":"https://openalex.org/I153473198","display_name":"North China Electric Power University","ror":"https://ror.org/04qr5t414","country_code":"CN","type":"education","lineage":["https://openalex.org/I153473198"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baicun Guo","raw_affiliation_strings":["Computer Science, North China Electric Power University, China"],"raw_orcid":"https://orcid.org/0000-0002-2755-2687","affiliations":[{"raw_affiliation_string":"Computer Science, North China Electric Power University, China","institution_ids":["https://openalex.org/I153473198"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5087428737"],"corresponding_institution_ids":["https://openalex.org/I153473198"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23729347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9983000159263611,"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":0.9915000200271606,"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":0.8228159546852112},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7691059708595276},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.7243960499763489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5917149186134338},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.5398558378219604},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.4688476324081421},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44324713945388794},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39860349893569946},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34123149514198303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3300510048866272},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05440640449523926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8228159546852112},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7691059708595276},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.7243960499763489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5917149186134338},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.5398558378219604},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.4688476324081421},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44324713945388794},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39860349893569946},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34123149514198303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3300510048866272},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05440640449523926},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3577164.3577165","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577164.3577165","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577164.3577165","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 4th International Conference on Video, Signal and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3577164.3577165","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577164.3577165","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577164.3577165","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 4th International Conference on Video, Signal and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4362564497.pdf","grobid_xml":"https://content.openalex.org/works/W4362564497.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W117491841","https://openalex.org/W1977654659","https://openalex.org/W1986926502","https://openalex.org/W2085039473","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2142159465","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2239285313","https://openalex.org/W2519818067","https://openalex.org/W2550687635","https://openalex.org/W2604243686","https://openalex.org/W2605076167","https://openalex.org/W2965066169","https://openalex.org/W4403280574","https://openalex.org/W6600319451","https://openalex.org/W6629282964","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2334580170"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,36,55],"improve":[4,48],"the":[5,21,39,59,63,67],"natural":[6,31],"scene":[7],"text":[8,25],"detection":[9,26],"and":[10,17,27,44,47,52,57],"recognition":[11,28],"technology":[12],"based":[13],"on":[14,38],"2d":[15],"attention":[16],"encoder-decoder":[18,42],"framework.":[19],"Firstly,":[20],"related":[22],"work":[23,37],"of":[24,41,66],"in":[29],"different":[30],"view":[32],"is":[33],"discussed.":[34],"Secondly,":[35],"basis":[40],"framework":[43],"two-dimention":[45],"module,":[46],"it":[49],"through":[50],"aggregation":[51],"hybridisation.":[53],"Finally,":[54],"discussed":[56],"analyzed":[58],"results,and":[60],"figured":[61],"out":[62],"possible":[64],"shortcomings":[65],"model.":[68]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}