{"id":"https://openalex.org/W4404239097","doi":"https://doi.org/10.1109/tpami.2024.3495831","title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","display_name":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","publication_year":2024,"publication_date":"2024-11-11","ids":{"openalex":"https://openalex.org/W4404239097","doi":"https://doi.org/10.1109/tpami.2024.3495831","pmid":"https://pubmed.ncbi.nlm.nih.gov/39527443"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3495831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3495831","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5070541608","display_name":"Maoyuan Ye","orcid":"https://orcid.org/0000-0002-4180-1096"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maoyuan Ye","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4180-1096","affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345321","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-6595-7661"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6595-7661","affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026501335","display_name":"Juhua Liu","orcid":"https://orcid.org/0000-0002-3907-8820"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juhua Liu","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3907-8820","affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenyu Liu","orcid":"https://orcid.org/0009-0006-6682-2877"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyu Liu","raw_affiliation_strings":["iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China","iFLYTEK Research, IFLYTEK CO. LTD., China"],"raw_orcid":"https://orcid.org/0009-0006-6682-2877","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"iFLYTEK Research, IFLYTEK CO. LTD., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059859891","display_name":"Baocai Yin","orcid":"https://orcid.org/0000-0002-4164-6647"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baocai Yin","raw_affiliation_strings":["iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China","iFLYTEK Research, IFLYTEK CO. LTD., China"],"raw_orcid":"https://orcid.org/0000-0002-4164-6647","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"iFLYTEK Research, IFLYTEK CO. LTD., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cong Liu","orcid":"https://orcid.org/0009-0003-0328-423X"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Liu","raw_affiliation_strings":["iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China","iFLYTEK Research, IFLYTEK CO. LTD., China"],"raw_orcid":"https://orcid.org/0009-0003-0328-423X","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"iFLYTEK Research, IFLYTEK CO. LTD., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060042752","display_name":"Bo Du","orcid":"https://orcid.org/0000-0002-0059-8458"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Du","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-0059-8458","affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["College of Computing & Data Science, Nanyang Technological University, Singapore","College of Computing & Data Science, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"College of Computing & Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"College of Computing & Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.5276,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.99260199,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"47","issue":"3","first_page":"1431","last_page":"1447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.855400025844574,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.855400025844574,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.8309000134468079,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.8025000095367432,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.635069727897644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6301293969154358},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.610167920589447},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5812703371047974},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4126776158809662},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4037902355194092},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3990519046783447}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.635069727897644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6301293969154358},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.610167920589447},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5812703371047974},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4126776158809662},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4037902355194092},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3990519046783447}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2024.3495831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3495831","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39527443","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39527443","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:dr.ntu.edu.sg:10356/218166","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/218166","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G1836220556","display_name":null,"funder_award_id":"62225113","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3648843532","display_name":null,"funder_award_id":"U23B2048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5586136776","display_name":null,"funder_award_id":"2022YFB4500600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8400922664","display_name":null,"funder_award_id":"2023YFC2705700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8527334069","display_name":null,"funder_award_id":"62076186","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W1972065312","https://openalex.org/W2144554289","https://openalex.org/W2550687635","https://openalex.org/W2784050770","https://openalex.org/W2786162033","https://openalex.org/W2787091153","https://openalex.org/W2914492226","https://openalex.org/W2962914239","https://openalex.org/W2963150697","https://openalex.org/W2963299604","https://openalex.org/W2963351448","https://openalex.org/W2963647456","https://openalex.org/W2967615747","https://openalex.org/W2972678073","https://openalex.org/W2991626090","https://openalex.org/W2998621280","https://openalex.org/W2999219213","https://openalex.org/W3003218881","https://openalex.org/W3003711898","https://openalex.org/W3003791552","https://openalex.org/W3003921261","https://openalex.org/W3014641072","https://openalex.org/W3014690505","https://openalex.org/W3034792612","https://openalex.org/W3035222584","https://openalex.org/W3096609285","https://openalex.org/W3168428721","https://openalex.org/W3168649818","https://openalex.org/W3172799005","https://openalex.org/W3173325518","https://openalex.org/W3176659256","https://openalex.org/W3176664887","https://openalex.org/W3179897446","https://openalex.org/W3181016597","https://openalex.org/W3184364189","https://openalex.org/W3194824089","https://openalex.org/W4283276297","https://openalex.org/W4304013646","https://openalex.org/W4312230431","https://openalex.org/W4312233877","https://openalex.org/W4312351507","https://openalex.org/W4312874706","https://openalex.org/W4312988011","https://openalex.org/W4313006333","https://openalex.org/W4313156423","https://openalex.org/W4313172891","https://openalex.org/W4320481960","https://openalex.org/W4323892169","https://openalex.org/W4380839071","https://openalex.org/W4382464147","https://openalex.org/W4386065412","https://openalex.org/W4386075493","https://openalex.org/W4386075667","https://openalex.org/W4386083034","https://openalex.org/W4386159110","https://openalex.org/W4387968066","https://openalex.org/W4387968089","https://openalex.org/W4388188651","https://openalex.org/W4390874575","https://openalex.org/W4392980188","https://openalex.org/W4393159543","https://openalex.org/W4394625591","https://openalex.org/W4402916145","https://openalex.org/W4404722477","https://openalex.org/W6691603626","https://openalex.org/W6757817989","https://openalex.org/W6779823529","https://openalex.org/W6784930956","https://openalex.org/W6791353385","https://openalex.org/W6797399245","https://openalex.org/W6803794721","https://openalex.org/W6810479921","https://openalex.org/W6846178434","https://openalex.org/W6851980744","https://openalex.org/W6852276098","https://openalex.org/W6852501939","https://openalex.org/W6852612167","https://openalex.org/W6852629184","https://openalex.org/W6852694211","https://openalex.org/W6852909635","https://openalex.org/W6853219587","https://openalex.org/W6853702739","https://openalex.org/W6854362512","https://openalex.org/W6855838334","https://openalex.org/W6859457051","https://openalex.org/W6860696803"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4385583601","https://openalex.org/W4395685956","https://openalex.org/W3159516372","https://openalex.org/W4398146871","https://openalex.org/W1522196789"],"abstract_inverted_index":{"The":[0],"Segment":[1],"Anything":[2],"Model":[3],"(SAM),":[4],"a":[5,12,30,65,73,90,121,180],"profound":[6],"vision":[7],"foundation":[8],"model":[9,32,71,81],"pretrained":[10],"on":[11,116,196,201,220,231,240],"large-scale":[13],"dataset,":[14],"breaks":[15],"the":[16,85,96,101,111,117,142,169,187,210,232,241],"boundaries":[17],"of":[18,190],"general":[19],"segmentation":[20,42,69,138],"and":[21,51,136,161,176,198,217,228,237],"sparks":[22],"various":[23],"downstream":[24],"applications.":[25],"This":[26],"paper":[27],"introduces":[28],"Hi-SAM,":[29],"unified":[31],"leveraging":[33],"SAM":[34,63],"for":[35,156,168,203,213],"hierarchical":[36,123,157,215],"text":[37,68,87,98,148,158,205],"segmentation.":[38,206],"Hi-SAM":[39,114,128,145,172,222],"excels":[40],"in":[41,89,100,165],"across":[43,95],"four":[44,97],"hierarchies,":[45],"including":[46],"pixel-level":[47,67,86,147,204],"text,":[48],"word,":[49,174],"text-line,":[50,175],"paragraph,":[52],"while":[53],"realizing":[54],"layout":[55,163,218,244],"analysis":[56,164,219],"as":[57],"well.":[58],"Specifically,":[59],"we":[60,109],"first":[61],"turn":[62],"into":[64],"high-quality":[66],"(TS)":[70],"through":[72],"parameter-efficient":[74],"fine-tuning":[75],"approach.":[76],"We":[77],"use":[78],"this":[79],"TS":[80,118,192],"to":[82,209],"iteratively":[83],"generate":[84],"labels":[88,94],"semi-automatical":[91],"manner,":[92],"unifying":[93],"hierarchies":[99],"HierText":[102],"dataset.":[103],"Subsequently,":[104],"with":[105,120,179],"these":[106],"complete":[107],"labels,":[108],"launch":[110],"end-to-end":[112],"trainable":[113],"based":[115],"architecture":[119],"customized":[122],"mask":[124,132,159],"decoder.":[125],"During":[126],"inference,":[127],"offers":[129],"both":[130],"automatic":[131],"generation":[133,160],"(AMG)":[134],"mode":[135],"promptable":[137],"(PS)":[139],"mode.":[140],"In":[141],"AMG":[143],"mode,":[144,171],"segments":[146],"foreground":[149,154],"masks":[150,178],"initially,":[151],"then":[152],"samples":[153],"points":[155],"achieves":[162,223],"passing.":[166],"As":[167],"PS":[170],"provides":[173],"paragraph":[177,242],"single":[181],"point":[182],"click.":[183],"Experimental":[184],"results":[185],"show":[186],"state-of-the-art":[188],"performance":[189],"our":[191],"model:":[193],"84.86%":[194],"fgIOU":[195,200],"Total-Text":[197],"88.96%":[199],"TextSeg":[202],"Moreover,":[207],"compared":[208],"previous":[211],"specialist":[212],"joint":[214],"detection":[216],"HierText,":[221],"significant":[224],"improvements:":[225],"4.73%":[226],"PQ":[227,236],"5.39%":[229],"F1":[230,239],"text-line":[233],"level,":[234],"5.49%":[235],"7.39%":[238],"level":[243],"analysis,":[245],"requiring":[246],"fewer":[247],"training":[248],"epochs.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":19}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}