{"id":"https://openalex.org/W4406354695","doi":"https://doi.org/10.1109/tpami.2025.3528950","title":"VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-Domain Generalization","display_name":"VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-Domain Generalization","publication_year":2025,"publication_date":"2025-01-14","ids":{"openalex":"https://openalex.org/W4406354695","doi":"https://doi.org/10.1109/tpami.2025.3528950","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031074"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3528950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3528950","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/A5100389396","display_name":"Yuliang Liu","orcid":"https://orcid.org/0000-0002-3037-173X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuliang Liu","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787743","display_name":"Mingxin Huang","orcid":"https://orcid.org/0009-0002-5736-959X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxin Huang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015410459","display_name":"Hao Yan","orcid":"https://orcid.org/0009-0007-7750-0758"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yan","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104219045","display_name":"Linger Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linger Deng","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101634167","display_name":"Weijia Wu","orcid":"https://orcid.org/0000-0003-3912-7212"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijia Wu","raw_affiliation_strings":["Zhejiang University, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033681666","display_name":"Hao L\u00fc","orcid":"https://orcid.org/0000-0003-3854-8664"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Lu","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006294869","display_name":"Chunhua Shen","orcid":"https://orcid.org/0000-0002-8648-8718"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhua Shen","raw_affiliation_strings":["Zhejiang University, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080674767","display_name":"Lianwen Jin","orcid":"https://orcid.org/0000-0002-5456-0957"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianwen Jin","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Bai","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100389396"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":2.4362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86646489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"47","issue":"4","first_page":"2957","last_page":"2972"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.982699990272522,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.982699990272522,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9684000015258789,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9553999900817871,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6696064472198486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6664482355117798},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6349297761917114},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.545053243637085},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5339115262031555},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45231905579566956},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4280849099159241},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39499926567077637},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17851674556732178}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6696064472198486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664482355117798},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6349297761917114},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.545053243637085},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5339115262031555},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45231905579566956},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4280849099159241},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39499926567077637},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17851674556732178},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3528950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3528950","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:40031074","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031074","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4189157326","display_name":null,"funder_award_id":"62225603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5777740948","display_name":null,"funder_award_id":"62206104","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6561198578","display_name":null,"funder_award_id":"62476093","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6852825479","display_name":null,"funder_award_id":"61936003","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":104,"referenced_works":["https://openalex.org/W1569095176","https://openalex.org/W1905722737","https://openalex.org/W1922126009","https://openalex.org/W1998981432","https://openalex.org/W2008806374","https://openalex.org/W2019660985","https://openalex.org/W2083442372","https://openalex.org/W2085261163","https://openalex.org/W2099614498","https://openalex.org/W2104946622","https://openalex.org/W2142159465","https://openalex.org/W2144554289","https://openalex.org/W2148214126","https://openalex.org/W2158592639","https://openalex.org/W2163292664","https://openalex.org/W2222512263","https://openalex.org/W2340583188","https://openalex.org/W2343052201","https://openalex.org/W2522182470","https://openalex.org/W2593768305","https://openalex.org/W2596297229","https://openalex.org/W2604735854","https://openalex.org/W2605982830","https://openalex.org/W2618799552","https://openalex.org/W2785383245","https://openalex.org/W2786502936","https://openalex.org/W2799067027","https://openalex.org/W2808206204","https://openalex.org/W2914492226","https://openalex.org/W2948069880","https://openalex.org/W2959965583","https://openalex.org/W2962766617","https://openalex.org/W2962986948","https://openalex.org/W2963351448","https://openalex.org/W2963916161","https://openalex.org/W2964018263","https://openalex.org/W2964296749","https://openalex.org/W2965463054","https://openalex.org/W2968226676","https://openalex.org/W2970910956","https://openalex.org/W2981969038","https://openalex.org/W2982121298","https://openalex.org/W2987563462","https://openalex.org/W2988098900","https://openalex.org/W2991626090","https://openalex.org/W2991699366","https://openalex.org/W2998621280","https://openalex.org/W3034792612","https://openalex.org/W3095753995","https://openalex.org/W3096609285","https://openalex.org/W3106879600","https://openalex.org/W3106963860","https://openalex.org/W3109908659","https://openalex.org/W3110398855","https://openalex.org/W3120080989","https://openalex.org/W3159307593","https://openalex.org/W3160608582","https://openalex.org/W3174658120","https://openalex.org/W3175961224","https://openalex.org/W3178292378","https://openalex.org/W3181186176","https://openalex.org/W3196976036","https://openalex.org/W3204971388","https://openalex.org/W4214922754","https://openalex.org/W4225683503","https://openalex.org/W4304084026","https://openalex.org/W4304091583","https://openalex.org/W4310335763","https://openalex.org/W4312230431","https://openalex.org/W4312351507","https://openalex.org/W4312473433","https://openalex.org/W4312960652","https://openalex.org/W4382464147","https://openalex.org/W4385768155","https://openalex.org/W4386065412","https://openalex.org/W4386075667","https://openalex.org/W4386159002","https://openalex.org/W4386453743","https://openalex.org/W4388543952","https://openalex.org/W4389705007","https://openalex.org/W4390872934","https://openalex.org/W4390873054","https://openalex.org/W4390874051","https://openalex.org/W4390874575","https://openalex.org/W4392980188","https://openalex.org/W4400584620","https://openalex.org/W4402702999","https://openalex.org/W4402716330","https://openalex.org/W4402727764","https://openalex.org/W4402774225","https://openalex.org/W4405399726","https://openalex.org/W6757817989","https://openalex.org/W6759579507","https://openalex.org/W6784094891","https://openalex.org/W6791353385","https://openalex.org/W6797979884","https://openalex.org/W6805458221","https://openalex.org/W6811230874","https://openalex.org/W6852629184","https://openalex.org/W6857461731","https://openalex.org/W6858433780","https://openalex.org/W6860041859","https://openalex.org/W6861503643","https://openalex.org/W6862276026"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W2990774877","https://openalex.org/W3093339210"],"abstract_inverted_index":{"Text":[0],"spotting,":[1,211],"a":[2,31,54,60,71,121,126],"task":[3],"involving":[4],"the":[5,38,42,66,97,101,114,135,145,171,189],"extraction":[6],"of":[7,41,151,186],"textual":[8],"information":[9,119],"from":[10],"image":[11,77],"or":[12],"video":[13,79,128,174,179],"sequences,":[14],"faces":[15],"challenges":[16],"in":[17,153,177,206,212],"cross-domain":[18,155,165,208],"adaption,":[19,166],"such":[20,157],"as":[21,158],"image-to-image":[22],"and":[23,59,78,161,180,223],"image-to-video":[24],"generalization.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,52,124],"introduce":[30],"new":[32],"method,":[33],"termed":[34],"VimTS,":[35],"which":[36,218],"enhances":[37],"generalization":[39],"ability":[40],"model":[43,69,73,102,115,217],"by":[44,133,148,183],"achieving":[45],"better":[46],"synergy":[47],"among":[48],"different":[49,94],"tasks.":[50],"Typically,":[51],"propose":[53,125],"Prompt":[55,86],"Queries":[56,87],"Generation":[57,88],"Module":[58,89],"Tasks-aware":[61,98],"Adapter":[62,99],"to":[63,111,116,214],"effectively":[64],"convert":[65],"original":[67],"single-task":[68],"into":[70],"multi-task":[72],"suitable":[74,105],"for":[75,107],"both":[76],"scenarios":[80],"with":[81],"minimal":[82],"additional":[83],"parameters.":[84],"The":[85],"facilitates":[90],"explicit":[91],"interaction":[92],"between":[93],"tasks,":[95],"while":[96],"helps":[100],"dynamically":[103],"learn":[104,117],"features":[106],"each":[108],"task.":[109],"Additionally,":[110],"further":[112,197],"enable":[113],"temporal":[118],"at":[120],"lower":[122],"cost,":[123],"synthetic":[127],"text":[129,210],"dataset":[130],"(VTD-368":[131],"k)":[132],"leveraging":[134],"Content":[136],"Deformation":[137],"Fields":[138],"(CoDeF)":[139],"algorithm.":[140],"Notably,":[141],"our":[142,167,215],"method":[143,147,168,176],"outperforms":[144],"state-of-the-art":[146],"an":[149,184],"average":[150,185],"2.6%":[152],"six":[154],"benchmarks":[156],"TT-to-IC15,":[159],"CTW1500-to-TT,":[160],"TT-to-CTW1500.":[162],"For":[163],"video-level":[164],"even":[169],"surpasses":[170],"previous":[172],"end-to-end":[173],"spotting":[175],"ICDAR2015":[178],"DSText":[181],"v2":[182],"5.5%":[187],"on":[188],"MOTA":[190],"metric,":[191],"using":[192],"only":[193],"image-level":[194],"data.":[195,224],"We":[196],"demonstrate":[198],"that":[199],"existing":[200],"Large":[201],"Multimodal":[202],"Models":[203],"exhibit":[204],"limitations":[205],"generating":[207],"scene":[209],"contrast":[213],"VimTS":[216],"requires":[219],"significantly":[220],"fewer":[221],"parameters":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}