{"id":"https://openalex.org/W7117959061","doi":"https://doi.org/10.1007/978-3-032-07343-3_13","title":"SAViL-Det: Semantic-Aware Vision-Language Model for Multi-script Text Detection","display_name":"SAViL-Det: Semantic-Aware Vision-Language Model for Multi-script Text Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7117959061","doi":"https://doi.org/10.1007/978-3-032-07343-3_13"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-07343-3_13","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-07343-3_13","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5035255332","display_name":"Mohammed-En-nadhir Zighem","orcid":null},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210141120","display_name":"Sorbonne University Abu Dhabi","ror":"https://ror.org/03e1ymy32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210141120"]}],"countries":["AE","FR"],"is_corresponding":true,"raw_author_name":"Mohammed-En-Nadhir Zighem","raw_affiliation_strings":["Sorbonne Center for Artificial Intelligence, Sorbonne University Abu Dhabi, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0003-4796-8230","affiliations":[{"raw_affiliation_string":"Sorbonne Center for Artificial Intelligence, Sorbonne University Abu Dhabi, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210141120","https://openalex.org/I39804081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013928164","display_name":"Abdenour Hadid","orcid":"https://orcid.org/0000-0001-9092-735X"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210141120","display_name":"Sorbonne University Abu Dhabi","ror":"https://ror.org/03e1ymy32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210141120"]}],"countries":["AE","FR"],"is_corresponding":false,"raw_author_name":"Abdenour Hadid","raw_affiliation_strings":["Sorbonne Center for Artificial Intelligence, Sorbonne University Abu Dhabi, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0001-9092-735X","affiliations":[{"raw_affiliation_string":"Sorbonne Center for Artificial Intelligence, Sorbonne University Abu Dhabi, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210141120","https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035255332"],"corresponding_institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210141120"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01219843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.6466000080108643,"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":0.6466000080108643,"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":0.24719999730587006,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.022600000724196434,"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/scripting-language","display_name":"Scripting language","score":0.6288999915122986},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5720999836921692},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5638999938964844},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.4440000057220459},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.43130001425743103},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4050999879837036},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.40450000762939453},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3995000123977661},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3928999900817871}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9017999768257141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6579999923706055},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5720999836921692},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5638999938964844},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44269999861717224},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.40450000762939453},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.35019999742507935},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3228999972343445},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.31679999828338623},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C202708506","wikidata":"https://www.wikidata.org/wiki/Q7449050","display_name":"Semantic compression","level":5,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-032-07343-3_13","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-07343-3_13","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-05453155v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05453155","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advanced Concepts for Intelligent Vision Systems, ACIVS 2025, Jul 2025, Tokyo, Japan. 15656, Springer Nature Switzerland, pp.159-171, 2026, Lecture Notes in Computer Science, &#x27E8;10.1007/978-3-032-07343-3_13&#x27E9;","raw_type":"Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47369012236595154}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2008806374","https://openalex.org/W2605982830","https://openalex.org/W2810028092","https://openalex.org/W2914492226","https://openalex.org/W2962810613","https://openalex.org/W2963353821","https://openalex.org/W2963647456","https://openalex.org/W2967615747","https://openalex.org/W2991626090","https://openalex.org/W3003868038","https://openalex.org/W3181016597","https://openalex.org/W4214922754","https://openalex.org/W4312230431","https://openalex.org/W4313006333","https://openalex.org/W4313172891","https://openalex.org/W4382464147","https://openalex.org/W4386065412","https://openalex.org/W4386075667","https://openalex.org/W4391307079","https://openalex.org/W4393149654"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2026-01-02T00:00:00"}
