{"id":"https://openalex.org/W4388188651","doi":"https://doi.org/10.1145/3581783.3612243","title":"Weakly-Supervised Text Instance Segmentation","display_name":"Weakly-Supervised Text Instance Segmentation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388188651","doi":"https://doi.org/10.1145/3581783.3612243"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5023916837","display_name":"Xinyan Zu","orcid":"https://orcid.org/0000-0001-6374-3344"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyan Zu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080937507","display_name":"Haiyang Yu","orcid":"https://orcid.org/0000-0002-1717-0474"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Yu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365239","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-9633-0033"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Xue","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023916837"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.7379,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73440876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1915","last_page":"1923"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.6986809372901917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6235302686691284},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5862697958946228},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4842938780784607},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4222426414489746},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4192469120025635},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36702078580856323},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3432602882385254}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6986809372901917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6235302686691284},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5862697958946228},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4842938780784607},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4222426414489746},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4192469120025635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36702078580856323},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3432602882385254}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2612809889","display_name":null,"funder_award_id":"62176060","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3921780379","display_name":null,"funder_award_id":"20511100400","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1621043042","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W2161236525","https://openalex.org/W2194187530","https://openalex.org/W2295107390","https://openalex.org/W2343052201","https://openalex.org/W2952793010","https://openalex.org/W2963299604","https://openalex.org/W2963311325","https://openalex.org/W2963353821","https://openalex.org/W2964309882","https://openalex.org/W2965066169","https://openalex.org/W2972678073","https://openalex.org/W2988326850","https://openalex.org/W2991090032","https://openalex.org/W3035703639","https://openalex.org/W3042760913","https://openalex.org/W3109301572","https://openalex.org/W3170544306","https://openalex.org/W3177505580","https://openalex.org/W3211490618","https://openalex.org/W4225562651","https://openalex.org/W4226544595","https://openalex.org/W4295928229","https://openalex.org/W4304080333","https://openalex.org/W4312593844","https://openalex.org/W4382202677"],"related_works":["https://openalex.org/W1986655823","https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W3144569342","https://openalex.org/W3011384228","https://openalex.org/W2945274617","https://openalex.org/W3199300986","https://openalex.org/W4313052709","https://openalex.org/W4298131179","https://openalex.org/W2375430703"],"abstract_inverted_index":{"Text":[0,76],"segmentation":[1,14,43,100,112,133,173],"is":[2],"a":[3,25,74,92,98,126],"challenging":[4],"computer":[5],"vision":[6],"task":[7],"with":[8,20],"many":[9],"downstream":[10],"applications.":[11],"Current":[12],"text":[13,41,46,49,54,66,93,99,142],"models":[15,56],"need":[16],"to":[17,38,59,81,102,110],"be":[18],"trained":[19],"pixel-level":[21],"annotations,":[22],"which":[23,114],"requires":[24],"lot":[26],"of":[27,64,91,139,154,196],"labor":[28],"cost.":[29],"In":[30,122],"this":[31,70],"paper,":[32],"we":[33,72,96,124],"take":[34,103],"the":[35,61,83,88,104,118,132,140,146,152,164,168,190,197,206],"first":[36],"attempt":[37],"perform":[39],"weakly-supervised":[40,171],"instance":[42,204],"through":[44],"bridging":[45],"recognition":[47,55,156],"and":[48,149,157,177,183,188,215,219,223],"segmentation.":[50,158],"We":[51],"observe":[52],"that":[53,163],"are":[57,115,226],"able":[58],"produce":[60],"attention":[62,89,106],"localization":[63],"each":[65],"instance.":[67],"Based":[68],"on":[69,87,181,203,217],"observation,":[71],"propose":[73],"two-stage":[75],"Adaptive":[77],"Refinement":[78],"(TAR)":[79],"module":[80,101],"generate":[82],"pseudo":[84,120],"labels":[85],"based":[86],"map":[90],"recognizer.":[94],"Meanwhile,":[95],"develop":[97],"rough":[105],"location":[107],"as":[108,135],"input":[109,141],"predict":[111],"masks,":[113],"supervised":[116],"by":[117,130,175,213],"aforementioned":[119],"labels.":[121],"addition,":[123],"introduce":[125],"mask-augmented":[127],"contrastive":[128],"learning":[129],"treating":[131],"result":[134],"an":[136],"augmented":[137],"version":[138],"image,":[143],"thus":[144],"improving":[145],"visual":[147],"representation":[148],"further":[150],"enhancing":[151],"performance":[153],"both":[155],"The":[159],"experimental":[160],"results":[161],"demonstrate":[162],"proposed":[165,191,207],"method":[166,192,208],"outperforms":[167],"state-of-the-art":[169],"(SOTA)":[170],"generic":[172],"methods":[174,212],"18.95%":[176],"17.80%":[178],"in":[179],"fgIoU":[180],"ICDAR13-FST":[182,218],"TextSeg.":[184],"On":[185],"MLT-S,":[186],"COCO-TS":[187],"Total-Text,":[189],"achieves":[193],"about":[194],"82%":[195],"fully-supervised":[198],"methods'":[199],"performance.":[200],"When":[201],"evaluated":[202],"segmentation,":[205],"exceeds":[209],"existing":[210],"SOTA":[211],"23.32%":[214],"21.34%":[216],"TextSeg,":[220],"respectively.":[221],"Code":[222],"Supplementary":[224],"Materials":[225],"available":[227],"at":[228],"https://github.com/FudanVI/FudanOCR/tree/main/weakly-text-segmentation.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}