{"id":"https://openalex.org/W4387968089","doi":"https://doi.org/10.1145/3581783.3611769","title":"Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition","display_name":"Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968089","doi":"https://doi.org/10.1145/3581783.3611769"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611769","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5100742339","display_name":"Zixiao Wang","orcid":"https://orcid.org/0000-0002-0009-5033"},"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":true,"raw_author_name":"Zixiao Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"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/A5078162380","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0002-6249-5315"},"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":"Hongtao Xie","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"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/A5100427468","display_name":"Yuxin Wang","orcid":"https://orcid.org/0000-0002-0228-6220"},"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":"Yuxin Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"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/A5101531218","display_name":"Jianjun Xu","orcid":"https://orcid.org/0000-0001-6398-3364"},"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":"Jianjun Xu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"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/A5040360450","display_name":"Boqiang Zhang","orcid":"https://orcid.org/0000-0002-5314-4054"},"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":"Boqiang Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"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/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"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":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"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":6,"corresponding_author_ids":["https://openalex.org/A5100742339"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":3.3431,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94034506,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"509","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976999759674072,"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":0.9912999868392944,"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":0.7772222757339478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6269714832305908},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6185990571975708},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6036033034324646},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5470800995826721},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45662936568260193},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4532013535499573},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41441670060157776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3439270257949829},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22474277019500732},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10159552097320557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772222757339478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6269714832305908},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6185990571975708},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6036033034324646},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5470800995826721},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45662936568260193},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4532013535499573},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41441670060157776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3439270257949829},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22474277019500732},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10159552097320557},{"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:10.1145/3581783.3611769","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2182495747","display_name":null,"funder_award_id":"2121002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3828173677","display_name":null,"funder_award_id":"62121002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4897510482","display_name":null,"funder_award_id":"62232006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6695563415","display_name":null,"funder_award_id":"2022YFB3104700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G891989852","display_name":null,"funder_award_id":"62102384","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W2127141656","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2343052201","https://openalex.org/W2935842779","https://openalex.org/W2963233387","https://openalex.org/W2982157312","https://openalex.org/W2997749585","https://openalex.org/W2998382406","https://openalex.org/W3003921261","https://openalex.org/W3004846386","https://openalex.org/W3034447740","https://openalex.org/W3096739052","https://openalex.org/W3177684257","https://openalex.org/W3181186176","https://openalex.org/W3198377975","https://openalex.org/W3202415716","https://openalex.org/W3204479434","https://openalex.org/W3204510963","https://openalex.org/W4283819468","https://openalex.org/W4284961860","https://openalex.org/W4292825881","https://openalex.org/W4294982470","https://openalex.org/W4310335763","https://openalex.org/W4312420092","https://openalex.org/W4312563428","https://openalex.org/W4313045695","https://openalex.org/W6600234944","https://openalex.org/W6600553734"],"related_works":["https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2181948922","https://openalex.org/W2080152487","https://openalex.org/W2384362569","https://openalex.org/W2239445980","https://openalex.org/W2995553446","https://openalex.org/W2120455979"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,51],"explore":[4],"the":[5,8,61,65,71,76,104,124,141,149,154,166,172],"potential":[6],"of":[7,174],"Contrastive":[9],"Language-Image":[10],"Pretraining":[11],"(CLIP)":[12],"model":[13],"in":[14,37,64,107],"scene":[15],"text":[16,67,79,164],"recognition":[17],"(STR),":[18],"and":[19,34,163],"establish":[20],"a":[21,53,81,113,131,158],"novel":[22],"Symmetrical":[23],"Linguistic":[24,133],"Feature":[25],"Distillation":[26],"framework":[27],"(named":[28],"CLIP-OCR)":[29],"to":[30,119,139,156],"leverage":[31],"both":[32],"visual":[33,49,95],"linguistic":[35,62,98,142],"knowledge":[36,63],"CLIP.":[38],"Different":[39],"from":[40,103,117],"previous":[41],"CLIP-based":[42],"methods":[43],"mainly":[44],"considering":[45,145],"feature":[46,89,126],"generalization":[47],"on":[48,180],"encoding,":[50],"propose":[52],"symmetrical":[54,82],"distillation":[55],"strategy":[56],"(SDS)":[57],"that":[58,91],"further":[59],"captures":[60],"CLIP":[66,72,78],"encoder.":[68],"By":[69],"cascading":[70],"image":[73,162],"encoder":[74],"with":[75,86,176],"reversed":[77],"encoder,":[80],"structure":[83],"is":[84,137,153],"built":[85],"an":[87],"image-to-text":[88],"flow":[90,111],"covers":[92],"not":[93],"only":[94],"but":[96],"also":[97],"information":[99],"for":[100,165],"distillation.":[101],"Benefiting":[102],"natural":[105],"alignment":[106],"CLIP,":[108],"such":[109],"guidance":[110],"provides":[112],"progressive":[114],"optimization":[115],"objective":[116],"vision":[118],"language,":[120],"which":[121],"can":[122],"supervise":[123],"STR":[125,167,183],"forwarding":[127],"process":[128],"layer-by-layer.":[129],"Besides,":[130],"new":[132],"Consistency":[134],"Loss":[135],"(LCL)":[136],"proposed":[138],"enhance":[140],"capability":[143],"by":[144],"second-order":[146],"statistics":[147],"during":[148],"optimization.":[150],"Overall,":[151],"CLIP-OCR":[152,175],"first":[155],"design":[157],"smooth":[159],"transition":[160],"between":[161],"task.":[168],"Extensive":[169],"experiments":[170],"demonstrate":[171],"effectiveness":[173],"93.8%":[177],"average":[178],"accuracy":[179],"six":[181],"popular":[182],"benchmarks.":[184],"Code":[185],"will":[186],"be":[187],"available":[188],"at":[189],"https://github.com/wzx99/CLIPOCR.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
