{"id":"https://openalex.org/W4403792356","doi":"https://doi.org/10.1145/3664647.3680877","title":"Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval","display_name":"Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792356","doi":"https://doi.org/10.1145/3664647.3680877"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5046229717","display_name":"Gangyan Zeng","orcid":"https://orcid.org/0000-0003-2696-8549"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangyan Zeng","raw_affiliation_strings":["School of Cyber Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-2696-8549","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067423633","display_name":"Yuan Zhang","orcid":"https://orcid.org/0000-0003-3783-7974"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhang","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3783-7974","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674793","display_name":"Wei Jin","orcid":"https://orcid.org/0000-0003-2016-0901"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Wei","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2016-0901","affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016775929","display_name":"Dongbao Yang","orcid":"https://orcid.org/0000-0001-8628-411X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbao Yang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8628-411X","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044045771","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0001-9518-5914"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["School of Cyber Science and Engineering, Nanjing University of Science and Technology & Laboratory for Advanced Computing and Intelligence Engineering, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9518-5914","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Nanjing University of Science and Technology & Laboratory for Advanced Computing and Intelligence Engineering, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031034911","display_name":"Yiwen Gao","orcid":"https://orcid.org/0000-0001-5446-2014"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Gao","raw_affiliation_strings":["School of Cyber Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5446-2014","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014055218","display_name":"Xugong Qin","orcid":"https://orcid.org/0009-0004-3130-3220"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xugong Qin","raw_affiliation_strings":["School of Cyber Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-3130-3220","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016175345","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0003-4188-9953"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["TMCC, College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-4188-9953","affiliations":[{"raw_affiliation_string":"TMCC, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"2525","last_page":"2534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9977999925613403,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/focus","display_name":"Focus (optics)","score":0.867647111415863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7666128873825073},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5129365921020508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5016155242919922},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.48576977849006653},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43932682275772095},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2499028742313385}],"concepts":[{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.867647111415863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666128873825073},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5129365921020508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016155242919922},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.48576977849006653},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43932682275772095},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2499028742313385},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1922126009","https://openalex.org/W1986965125","https://openalex.org/W1998042868","https://openalex.org/W2012689760","https://openalex.org/W2053317383","https://openalex.org/W2123410090","https://openalex.org/W2142636459","https://openalex.org/W2160741934","https://openalex.org/W2766895242","https://openalex.org/W2888894220","https://openalex.org/W2962986948","https://openalex.org/W3003868038","https://openalex.org/W3080897988","https://openalex.org/W3086275027","https://openalex.org/W3110398855","https://openalex.org/W3152831436","https://openalex.org/W3177167102","https://openalex.org/W3179897446","https://openalex.org/W3198377975","https://openalex.org/W3206169490","https://openalex.org/W3206651063","https://openalex.org/W4225552434","https://openalex.org/W4253518031","https://openalex.org/W4296586882","https://openalex.org/W4304084224","https://openalex.org/W4312715377","https://openalex.org/W4317677707","https://openalex.org/W4321485374","https://openalex.org/W4386065412","https://openalex.org/W4386075561","https://openalex.org/W4386410320","https://openalex.org/W4387968089","https://openalex.org/W4387968277","https://openalex.org/W4387969748","https://openalex.org/W4388191243","https://openalex.org/W6782676154"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Scene":[0],"text":[1,11,30,62,77,82,109,116,122,129,199],"retrieval":[2,167,200],"aims":[3],"to":[4,19,49,114,170],"find":[5],"all":[6],"images":[7],"containing":[8],"the":[9,51,70,112,115,120,127,159,175,180],"query":[10,128,211],"from":[12,42],"an":[13,21],"image":[14],"gallery.":[15],"Current":[16],"efforts":[17],"tend":[18],"adopt":[20],"Optical":[22],"Character":[23],"Recognition":[24],"(OCR)":[25],"pipeline,":[26],"which":[27,139],"requires":[28],"complicated":[29],"detection":[31],"and/or":[32],"recognition":[33],"processes,":[34],"resulting":[35],"in":[36,44,138,206],"inefficient":[37],"and":[38,85,100,118,124,133,144,196],"inflexible":[39],"retrieval.":[40,63],"Different":[41],"them,":[43],"this":[45,91],"work":[46],"we":[47,67],"propose":[48],"explore":[50],"intrinsic":[52],"potential":[53],"of":[54,73,210],"Contrastive":[55],"Language-Image":[56],"Pre-training":[57],"(CLIP)":[58],"for":[59,136],"OCR-free":[60],"scene":[61,108,198],"Through":[64],"empirical":[65],"analysis,":[66],"observe":[68],"that":[69,155],"main":[71],"challenges":[72],"CLIP":[74],"as":[75],"a":[76,93,140,145,186],"retriever":[78],"are:":[79],"1)":[80],"limited":[81],"perceptual":[83],"scale,":[84],"2)":[86],"entangled":[87],"visual-semantic":[88],"concepts.":[89],"To":[90],"end,":[92],"novel":[94],"model":[95,182],"termed":[96],"FDP":[97,104,156,178],"(Focus,":[98],"Distinguish,":[99],"Prompt)":[101],"is":[102],"developed.":[103],"first":[105],"focuses":[106],"on":[107,174],"via":[110],"shifting":[111],"attention":[113],"area":[117],"probing":[119],"hidden":[121],"knowledge,":[123],"then":[125],"divides":[126],"into":[130],"content":[131],"word":[132,135],"function":[134],"processing,":[137],"semantic-aware":[141],"prompting":[142],"scheme":[143],"distracted":[146],"queries":[147],"assistance":[148],"module":[149],"are":[150],"utilized.":[151],"Extensive":[152],"experiments":[153,193],"show":[154],"significantly":[157],"enhances":[158],"inference":[160],"speed":[161],"while":[162],"achieving":[163],"better":[164],"or":[165],"competitive":[166],"accuracy":[168],"compared":[169],"existing":[171],"methods.":[172],"Notably,":[173],"IIIT-STR":[176],"benchmark,":[177],"surpasses":[179],"state-of-the-art":[181],"by":[183],"4.37%":[184],"with":[185],"4":[187],"times":[188],"faster":[189],"speed.":[190],"Furthermore,":[191],"additional":[192],"under":[194],"phrase-level":[195],"attribute-aware":[197],"settings":[201],"validate":[202],"FDP's":[203],"particular":[204],"advantages":[205],"handling":[207],"diverse":[208],"forms":[209],"text.":[212],"The":[213],"source":[214],"code":[215],"will":[216],"be":[217],"available":[218],"at":[219],"https://github.com/Gyann-z/FDP.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}