{"id":"https://openalex.org/W7171933600","doi":"https://doi.org/10.1145/3774521.3774556","title":"FormLens: From Ink to Insight with Adapting Vision-Language Models for Handwritten Form Digitization","display_name":"FormLens: From Ink to Insight with Adapting Vision-Language Models for Handwritten Form Digitization","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7171933600","doi":"https://doi.org/10.1145/3774521.3774556"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774556","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774556","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774556","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002057845","display_name":"Shaon Bhattacharyya","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shaon Bhattacharyya","raw_affiliation_strings":["CVIT, International Institute of Information Technology Hyderabad, Hyderabad, Telengana, India"],"raw_orcid":"https://orcid.org/0009-0009-8452-9043","affiliations":[{"raw_affiliation_string":"CVIT, International Institute of Information Technology Hyderabad, Hyderabad, Telengana, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052301812","display_name":"Ajoy Mondal","orcid":"https://orcid.org/0000-0002-4808-8860"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ajoy Mondal","raw_affiliation_strings":["CVIT, International Institute of Information Technology Hyderabad, Hyderabad, Telengana, India"],"raw_orcid":"https://orcid.org/0000-0002-4808-8860","affiliations":[{"raw_affiliation_string":"CVIT, International Institute of Information Technology Hyderabad, Hyderabad, Telengana, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. V. Jawahar","raw_affiliation_strings":["CVIT, International Institute of Information Technology Hyderabad, Hyderabad, Telengana, India"],"raw_orcid":"https://orcid.org/0000-0001-6767-7057","affiliations":[{"raw_affiliation_string":"CVIT, International Institute of Information Technology Hyderabad, Hyderabad, Telengana, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.8108999729156494},{"id":"https://openalex.org/keywords/handwriting","display_name":"Handwriting","score":0.7833999991416931},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.666700005531311},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5655999779701233},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.46129998564720154},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"Handwriting recognition","score":0.45980000495910645},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4352000057697296},{"id":"https://openalex.org/keywords/inkwell","display_name":"Inkwell","score":0.4172999858856201}],"concepts":[{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.8108999729156494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925000190734863},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.7833999991416931},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.666700005531311},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5655999779701233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5508000254631042},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.46129998564720154},{"id":"https://openalex.org/C112640561","wikidata":"https://www.wikidata.org/wiki/Q2440634","display_name":"Handwriting recognition","level":3,"score":0.45980000495910645},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4196000099182129},{"id":"https://openalex.org/C109693293","wikidata":"https://www.wikidata.org/wiki/Q1496072","display_name":"Inkwell","level":2,"score":0.4172999858856201},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4090000092983246},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39660000801086426},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3190999925136566},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C44868376","wikidata":"https://www.wikidata.org/wiki/Q3099089","display_name":"Intelligent character recognition","level":4,"score":0.305400013923645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.2700999975204468},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774556","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774556","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774556","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774556","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2001642682","https://openalex.org/W2132549764","https://openalex.org/W2233008261","https://openalex.org/W2491179239","https://openalex.org/W2605982830","https://openalex.org/W2809273748","https://openalex.org/W2962810613","https://openalex.org/W2964346820","https://openalex.org/W2967615747","https://openalex.org/W2986619406","https://openalex.org/W2997154779","https://openalex.org/W3112478873","https://openalex.org/W3118722740","https://openalex.org/W3174205643","https://openalex.org/W3176664887","https://openalex.org/W3197730340","https://openalex.org/W3202466114","https://openalex.org/W3205961173","https://openalex.org/W3217518891","https://openalex.org/W4214693170","https://openalex.org/W4285105124","https://openalex.org/W4304013646","https://openalex.org/W4304098321","https://openalex.org/W4312233877","https://openalex.org/W4367368531","https://openalex.org/W4382202677","https://openalex.org/W4386065837","https://openalex.org/W4400915096","https://openalex.org/W4415795229"],"related_works":[],"abstract_inverted_index":{"Handwritten":[0],"forms":[1,48,99],"are":[2,140],"still":[3],"widely":[4],"used":[5],"in":[6,132],"rural":[7],"banking,":[8],"healthcare,":[9],"and":[10,24,78,86,115,128,138],"public":[11],"administration":[12],"domains.":[13],"However,":[14],"their":[15],"large-scale":[16],"digitization":[17],"remains":[18],"difficult":[19],"due":[20],"to":[21,72,118],"handwriting":[22],"variability":[23],"the":[25],"limitations":[26],"of":[27,36,95],"conventional":[28],"OCR-based":[29],"systems.":[30],"We":[31],"introduce":[32],"FormLens,":[33],"an":[34],"adaptation":[35],"a":[37,66,92],"vision-language":[38],"model":[39],"for":[40],"end-to-end":[41],"form":[42],"understanding":[43],"that":[44,110],"directly":[45],"transforms":[46],"handwritten":[47,97,134],"into":[49],"structured":[50],"key-value":[51],"pairs":[52],"without":[53],"requiring":[54],"explicit":[55],"region":[56],"detection":[57],"or":[58],"OCR.":[59],"Built":[60],"via":[61],"Low-Rank":[62],"Adaptation":[63],"(LoRA)":[64],"on":[65],"multilingual":[67],"backbone,":[68],"FormLens":[69,111],"is":[70],"designed":[71],"handle":[73],"diverse":[74],"layouts,":[75],"noisy":[76],"backgrounds,":[77],"challenging":[79],"real-world":[80],"capture":[81],"conditions.":[82,106],"To":[83],"support":[84],"evaluation":[85],"domain":[87],"adaptation,":[88],"we":[89],"release":[90],"Form6000,":[91],"new":[93],"dataset":[94],"6,000":[96],"English":[98],"collected":[100],"from":[101],"650":[102],"individuals":[103],"under":[104],"varied":[105],"Extensive":[107],"experiments":[108],"demonstrate":[109],"achieves":[112],"superior":[113],"accuracy":[114],"robustness":[116],"compared":[117],"both":[119],"commercial":[120],"(e.g.,":[121],"Google":[122],"Form":[123,126],"Parser,":[124],"Azure":[125],"Recognizer)":[127],"open-source":[129],"baselines,":[130],"particularly":[131],"unconstrained":[133],"scenarios.":[135],"The":[136],"code":[137],"resources":[139],"available":[141],"at:":[142],"https://formlens.github.io/.":[143]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}