{"id":"https://openalex.org/W4386249516","doi":"https://doi.org/10.1145/3599957.3606219","title":"Weakly-supervised Semantic Segmentation on Historical Document Images","display_name":"Weakly-supervised Semantic Segmentation on Historical Document Images","publication_year":2023,"publication_date":"2023-08-06","ids":{"openalex":"https://openalex.org/W4386249516","doi":"https://doi.org/10.1145/3599957.3606219"},"language":"en","primary_location":{"id":"doi:10.1145/3599957.3606219","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3599957.3606219","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3599957.3606219?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3599957.3606219?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061711551","display_name":"Chulwoo Pack","orcid":"https://orcid.org/0000-0002-9876-4388"},"institutions":[{"id":"https://openalex.org/I177156846","display_name":"South Dakota State University","ror":"https://ror.org/015jmes13","country_code":"US","type":"education","lineage":["https://openalex.org/I177156846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chulwoo Pack","raw_affiliation_strings":["South Dakota State University, Brookings, South Dakota"],"raw_orcid":"https://orcid.org/0000-0002-9876-4388","affiliations":[{"raw_affiliation_string":"South Dakota State University, Brookings, South Dakota","institution_ids":["https://openalex.org/I177156846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007861098","display_name":"Dongyoun Kim","orcid":"https://orcid.org/0000-0002-7476-747X"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongyoun Kim","raw_affiliation_strings":["Iowa State University, Ames, Iowa"],"raw_orcid":"https://orcid.org/0000-0002-7476-747X","affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, Iowa","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1064,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37815793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9975000023841858,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9975000023841858,"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":0.9958000183105469,"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":0.9905999898910522,"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/computer-science","display_name":"Computer science","score":0.7938114404678345},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7455353140830994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7125674486160278},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5398496985435486},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5062059760093689},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5056462287902832},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5026195049285889},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.46754756569862366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45071941614151},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43735337257385254},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.411589115858078},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3920799493789673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7938114404678345},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7455353140830994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7125674486160278},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5398496985435486},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5062059760093689},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5056462287902832},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5026195049285889},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.46754756569862366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45071941614151},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43735337257385254},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.411589115858078},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3920799493789673},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3599957.3606219","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3599957.3606219","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3599957.3606219?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3599957.3606219","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3599957.3606219","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3599957.3606219?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386249516.pdf","grobid_xml":"https://content.openalex.org/works/W4386249516.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1495267108","https://openalex.org/W2055408294","https://openalex.org/W2295107390","https://openalex.org/W2337429362","https://openalex.org/W2746791238","https://openalex.org/W2768926640","https://openalex.org/W2787675099","https://openalex.org/W2798826627","https://openalex.org/W2962758679","https://openalex.org/W2962867364","https://openalex.org/W3104637907","https://openalex.org/W3161645848","https://openalex.org/W4200147393","https://openalex.org/W6742900778"],"related_works":["https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W3144569342","https://openalex.org/W2945274617","https://openalex.org/W4313052709","https://openalex.org/W2022929107","https://openalex.org/W2055202857","https://openalex.org/W80586315","https://openalex.org/W4205800335","https://openalex.org/W2758994127"],"abstract_inverted_index":{"Weakly-Supervised":[0],"Semantic":[1],"Segmentation":[2],"(WSSS)":[3],"has":[4],"been":[5],"widely":[6],"studied":[7],"as":[8,167],"a":[9,47,51,120,138,142,153,164,186,189,215],"feasible":[10],"option":[11,217],"to":[12,41,184],"reduce":[13],"the":[14,57,63,72,102,135,195,201,209,220,225],"expensive":[15],"annotation":[16],"costs":[17],"of":[18,54,59,66,75,104,137,160],"deep":[19],"semantic":[20,221],"segmentation":[21,78,139,190,222],"models.":[22],"While":[23],"numerous":[24],"studies":[25],"have":[26],"proposed":[27,210],"novel":[28],"approaches":[29],"for":[30,50,79,109,218],"generating":[31],"pseudo-labels":[32],"and":[33,71,181],"demonstrated":[34],"their":[35,37],"effectiveness,":[36],"domain":[38,58],"is":[39,46,113,175,192],"limited":[40],"natural":[42,93,110],"scene":[43,94,111],"images.":[44],"There":[45],"growing":[48,73],"need":[49],"comprehensive":[52],"exploration":[53],"WSSS":[55,106],"in":[56,141,224],"document":[60,69,76,84,205,226],"images,":[61,95],"given":[62],"increasing":[64],"number":[65],"digitized":[67],"historical":[68,204],"images":[70,85,112],"importance":[74],"image":[77,227],"successful":[80],"information":[81],"retrieval.":[82],"Importantly,":[83],"possess":[86],"inherent":[87],"characteristics":[88],"that":[89,208],"distinguish":[90],"them":[91],"from":[92],"rendering":[96],"conventional":[97],"image-level":[98,148],"labels":[99],"unsuitable.":[100],"Consequently,":[101],"application":[103],"recent":[105],"frameworks":[107],"designed":[108],"limited.":[114],"In":[115],"this":[116],"work,":[117],"we":[118],"propose":[119],"simple":[121,179],"yet":[122],"effective":[123],"pseudo-label":[124,211],"generation":[125,212],"technique":[126,213],"using":[127,194],"content-adaptive":[128],"geometric":[129],"feature":[130],"analysis.":[131],"This":[132],"approach":[133],"enables":[134],"training":[136,219],"model":[140,191,223],"weakly-supervised":[143],"manner":[144],"without":[145,162],"relying":[146],"on":[147,200],"labels.":[149],"Our":[150],"method":[151],"utilizes":[152],"Gravity-map,":[154],"which":[155],"can":[156],"highlight":[157],"potential":[158],"regions":[159],"interest":[161],"requiring":[163],"priori-knowledge,":[165],"serving":[166],"an":[168],"initial":[169],"coarse":[170],"pixel-level":[171],"label.":[172],"The":[173],"Gravity-map":[174],"subsequently":[176],"refined":[177],"through":[178],"binarization":[180],"noise":[182],"removal":[183],"form":[185],"pseudo-label.":[187],"Finally,":[188],"trained":[193],"generated":[196],"pseudo-labels.":[197],"Experimental":[198],"results":[199],"publicly":[202],"available":[203],"collection":[206],"demonstrate":[207],"offers":[214],"viable":[216],"domain.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}