{"id":"https://openalex.org/W7137853412","doi":"https://doi.org/10.1609/aaai.v40i13.38025","title":"ST-SAM: Multimodal Scene Text Segmentation with Dense Visual and Sparse Textual Prompts via SAM","display_name":"ST-SAM: Multimodal Scene Text Segmentation with Dense Visual and Sparse Textual Prompts via SAM","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137853412","doi":"https://doi.org/10.1609/aaai.v40i13.38025"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i13.38025","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38025","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i13.38025","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129733773","display_name":"Jin Wei","orcid":null},"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 AI Technology Center, CTOO, Lenovo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lenovo AI Technology Center, CTOO, Lenovo","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129716271","display_name":"Yaqiang Wu","orcid":null},"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":"Yaqiang Wu","raw_affiliation_strings":["Lenovo AI Technology Center, CTOO, Lenovo\nSchool of Computer Science and Technology, Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lenovo AI Technology Center, CTOO, Lenovo\nSchool of Computer Science and Technology, Xi'an Jiaotong University","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129741938","display_name":"Jiayi Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Yan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129671945","display_name":"Zeng Li","orcid":null},"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":"Zeng Li","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129711053","display_name":"Zhen Xu","orcid":null},"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":"Zhen Xu","raw_affiliation_strings":["Lenovo AI Technology Center, CTOO, Lenovo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lenovo AI Technology Center, CTOO, Lenovo","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129727305","display_name":"Yu Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132990","display_name":"State Key Laboratory of Cryptology","ror":"https://ror.org/02pn5rj08","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210132990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["VCIP & TMCC & DISSec, College of Computer Science & College of Cryptology and Cyber Science, Nankai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP & TMCC & DISSec, College of Computer Science & College of Cryptology and Cyber Science, Nankai University","institution_ids":["https://openalex.org/I4210132990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129681313","display_name":"Lingling Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingling Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129644393","display_name":"QianYing Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092558","display_name":"BC Platforms (Finland)","ror":"https://ror.org/002fen565","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210092558"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"QianYing Wang","raw_affiliation_strings":["Technology Strategy & Platforms, CTOO, Lenovo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Strategy & Platforms, CTOO, Lenovo","institution_ids":["https://openalex.org/I4210092558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06766382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"10530","last_page":"10538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.5343000292778015,"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":0.5343000292778015,"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":0.3675999939441681,"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":0.01489999983459711,"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/segmentation","display_name":"Segmentation","score":0.7936999797821045},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5734000205993652},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5388000011444092},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5073999762535095},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4713999927043915},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4458000063896179},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.41620001196861267},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4113999903202057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267999887466431},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7936999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6547999978065491},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5734000205993652},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5388000011444092},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46230000257492065},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4458000063896179},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41620001196861267},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41620001196861267},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4113999903202057},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.375},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.36890000104904175},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.35569998621940613},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.26750001311302185}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i13.38025","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38025","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/38025","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38025","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38025","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scene":[0],"text":[1,13,63,74,94,100,153,209],"segmentation":[2,14,44,75,95,154],"is":[3],"a":[4,19,83,104,108,126],"critical":[5],"preprocessing":[6],"step":[7],"in":[8],"various":[9],"text-based":[10],"applications.":[11],"Specialist":[12],"methods,":[15],"often":[16],"relying":[17,97],"on":[18,98,150,159,164,207],"detect-then-segment":[20,195],"paradigm,":[21],"tend":[22],"to":[23,30,57,88,116,185],"exhibit":[24],"reduced":[25],"robustness":[26],"and":[27,71,121,161,169],"can":[28],"lead":[29],"cascading":[31],"errors.":[32],"The":[33],"introduction":[34],"of":[35,138,188],"the":[36,136,139,181,186,194,199],"Segment":[37],"Anything":[38],"Model":[39],"(SAM)":[40],"has":[41],"revolutionized":[42],"general":[43,182],"by":[45,125,178],"leveraging":[46],"vision":[47],"foundation":[48],"models.":[49,171],"However,":[50],"SAM":[51,70,90,183],"still":[52,203],"falls":[53],"short":[54],"when":[55],"applied":[56],"domain-specific":[58],"tasks":[59],"such":[60],"as":[61,142],"scene":[62,73,93,152,189],"segmentation.":[64],"To":[65],"bridge":[66],"this":[67],"gap":[68],"between":[69],"specialized":[72],"approaches,":[76],"we":[77],"propose":[78],"ST-SAM":[79,102,141,145,173,197],"(Scene":[80],"Text":[81],"SAM),":[82],"parameter-efficient":[84],"fine-tuning":[85],"framework":[86],"tailored":[87],"adapt":[89],"for":[91],"high-quality":[92],"without":[96],"explicit":[99],"detection.":[101],"incorporates":[103],"multimodal":[105],"prompting":[106],"mechanism:":[107],"lightweight":[109],"visual":[110,119],"encoder":[111],"generates":[112],"multi-scale":[113],"spatial":[114],"features":[115],"provide":[117],"precise":[118],"context;":[120],"textual":[122],"prompts":[123],"generated":[124],"large":[127],"language":[128],"model":[129],"offer":[130],"high-level":[131],"semantic":[132],"guidance.":[133],"We":[134],"demonstrate":[135],"advantages":[137],"proposed":[140],"follows:":[143],"(1)":[144],"achieves":[146],"new":[147],"state-of-the-art":[148],"performance":[149,206],"multiple":[151],"benchmarks,":[155],"including":[156],"85.30%":[157],"fgIoU":[158,163],"Total-Text":[160],"91.03%":[162],"TextSeg,":[165],"outperforming":[166],"both":[167],"specialist":[168],"generalist":[170],"(2)":[172],"enables":[174],"effective":[175],"domain":[176,187],"adaptation":[177],"flexibly":[179],"adapting":[180],"architecture":[184],"text.":[190],"(3)":[191],"By":[192],"discarding":[193],"pipeline,":[196],"simplifies":[198],"inference":[200],"process":[201],"while":[202],"achieving":[204],"robust":[205],"complex":[208],"cases.":[210]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-18T00:00:00"}