{"id":"https://openalex.org/W4200334928","doi":"https://doi.org/10.1145/3490035.3490278","title":"Deformable deep networks for instance segmentation of overlapping multi page handwritten documents","display_name":"Deformable deep networks for instance segmentation of overlapping multi page handwritten documents","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4200334928","doi":"https://doi.org/10.1145/3490035.3490278"},"language":"en","primary_location":{"id":"doi:10.1145/3490035.3490278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490035.3490278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and Image Processing","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/A5013052430","display_name":"Sowmya Aitha","orcid":"https://orcid.org/0000-0003-2266-9947"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sowmya Aitha","raw_affiliation_strings":["IIIT Hyderabad, Hyderabad, INDIA"],"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, Hyderabad, INDIA","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082348012","display_name":"Sindhu Bollampalli","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sindhu Bollampalli","raw_affiliation_strings":["IIIT Hyderabad, Hyderabad, INDIA"],"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, Hyderabad, INDIA","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038936106","display_name":"Ravi Kiran Sarvadevabhatla","orcid":"https://orcid.org/0000-0003-4134-1154"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ravi Kiran Sarvadevabhatla","raw_affiliation_strings":["IIIT Hyderabad, Hyderabad, INDIA"],"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, Hyderabad, INDIA","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013052430"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.1921,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51197712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9865000247955322,"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/T11309","display_name":"Music and Audio Processing","score":0.9656999707221985,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7940660715103149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6353636384010315},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6131725311279297},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37391579151153564},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32227182388305664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940660715103149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6353636384010315},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6131725311279297},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37391579151153564},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32227182388305664}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3490035.3490278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490035.3490278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2019353007","https://openalex.org/W2085082924","https://openalex.org/W2154045346","https://openalex.org/W2443396451","https://openalex.org/W2576852589","https://openalex.org/W2601564443","https://openalex.org/W2781760569","https://openalex.org/W2786940623","https://openalex.org/W2793840492","https://openalex.org/W3003335109","https://openalex.org/W3003585861","https://openalex.org/W3003636685","https://openalex.org/W3003739041","https://openalex.org/W3004040469","https://openalex.org/W3004128655","https://openalex.org/W3006661061","https://openalex.org/W3023805750","https://openalex.org/W3035011051","https://openalex.org/W3107284742","https://openalex.org/W3109550678","https://openalex.org/W3167392131"],"related_works":["https://openalex.org/W4206076898","https://openalex.org/W2510758617","https://openalex.org/W2897195263","https://openalex.org/W4226401448","https://openalex.org/W2754350655","https://openalex.org/W2807253728","https://openalex.org/W3095523211","https://openalex.org/W2005476934","https://openalex.org/W2753174232","https://openalex.org/W2887603104"],"abstract_inverted_index":{"Digitizing":[0],"via":[1],"scanning":[2],"the":[3,8,38,52,110,145,183,186,190],"physical":[4],"artifact":[5],"often":[6,121],"forms":[7],"first":[9,39],"primary":[10],"step":[11],"in":[12,42,204],"preserving":[13],"historical":[14,200],"handwritten":[15,220],"manuscripts.":[16],"To":[17,126,143],"maximally":[18],"utilize":[19],"scanner":[20],"surface":[21],"area":[22],"and":[23,113,149,222],"minimize":[24],"manual":[25],"labor,":[26],"multiple":[27],"manuscripts":[28,54,82,103,221],"are":[29],"usually":[30],"scanned":[31,35,57],"together":[32],"into":[33],"a":[34,56,64,78,94,97,132],"image.":[36,84],"Therefore,":[37],"crucial":[40],"task":[41],"manuscript":[43,73,201],"content":[44],"understanding":[45,75],"is":[46,93,109],"to":[47,120,163],"ensure":[48],"that":[49],"each":[50,124],"of":[51,116,147,174,185,198],"individual":[53,102,199],"within":[55,219],"image":[58,135],"can":[59],"be":[60,89],"isolated":[61],"(segmented)":[62],"on":[63,211],"per-instance":[65],"basis.":[66],"Existing":[67],"deep":[68,151],"network":[69,152],"based":[70],"approaches":[71],"for":[72,96,189],"layout":[74],"implicitly":[76],"assume":[77],"single":[79],"or":[80],"two":[81],"per":[83],"Since":[85],"this":[86],"assumption":[87],"may":[88],"routinely":[90],"violated,":[91],"there":[92],"need":[95],"precursor":[98],"system":[99],"which":[100,159],"extracts":[101],"before":[104],"downstream":[105,212],"processing.":[106],"Another":[107],"challenge":[108],"highly":[111],"curved":[112],"deformed":[114],"boundaries":[115],"manuscripts,":[117],"causing":[118],"them":[119],"overlap":[122],"with":[123],"other.":[125],"tackle":[127],"such":[128,214],"challenges,":[129],"we":[130,154],"introduce":[131],"new":[133,187],"document":[134,176],"dataset":[136,148],"called":[137],"IMMI":[138],"(Indic":[139],"Multi":[140],"Manuscript":[141],"Images).":[142],"improve":[144],"efficiency":[146],"aid":[150],"training,":[153],"also":[155],"propose":[156],"an":[157],"approach":[158],"generates":[160],"synthetic":[161],"images":[162],"augment":[164],"sourced":[165],"non-synthetic":[166],"images.":[167],"We":[168],"conduct":[169],"experiments":[170],"using":[171],"modified":[172],"versions":[173],"existing":[175],"instance":[177,217],"segmentation":[178,218],"frameworks.":[179],"The":[180],"results":[181],"demonstrate":[182],"efficacy":[184],"frameworks":[188],"task.":[191],"Overall,":[192],"our":[193],"contributions":[194],"enable":[195,208],"robust":[196],"extraction":[197],"pages.":[202],"This":[203],"turn,":[205],"could":[206],"potentially":[207],"better":[209],"performance":[210],"tasks":[213],"as":[215],"region-level":[216],"optical":[223],"character":[224],"recognition.":[225]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}