{"id":"https://openalex.org/W4402427035","doi":"https://doi.org/10.1145/3663548.3675599","title":"EditScribe: Non-Visual Image Editing with Natural Language Verification Loops","display_name":"EditScribe: Non-Visual Image Editing with Natural Language Verification Loops","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4402427035","doi":"https://doi.org/10.1145/3663548.3675599"},"language":"en","primary_location":{"id":"doi:10.1145/3663548.3675599","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3663548.3675599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 26th International ACM SIGACCESS Conference on Computers and Accessibility","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.06632","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008164265","display_name":"Ruei-Che Chang","orcid":"https://orcid.org/0000-0001-7545-4136"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I4210111179","display_name":"Michigan United","ror":"https://ror.org/0291ys696","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210111179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruei-Che Chang","raw_affiliation_strings":["Computer Science and Engineering, University of Michigan, United States"],"raw_orcid":"https://orcid.org/0000-0001-7545-4136","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Michigan, United States","institution_ids":["https://openalex.org/I27837315","https://openalex.org/I4210111179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460407","display_name":"Yuxuan Liu","orcid":"https://orcid.org/0000-0002-3040-9857"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I4210111179","display_name":"Michigan United","ror":"https://ror.org/0291ys696","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210111179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxuan Liu","raw_affiliation_strings":["Computer Science and Engineering, University of Michigan, United States"],"raw_orcid":"https://orcid.org/0009-0005-5023-1426","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Michigan, United States","institution_ids":["https://openalex.org/I27837315","https://openalex.org/I4210111179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070705628","display_name":"Lotus Zhang","orcid":"https://orcid.org/0000-0002-6315-9970"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lotus Zhang","raw_affiliation_strings":["Human Centered Design and Engineering, University of Washington, United States"],"raw_orcid":"https://orcid.org/0000-0002-6315-9970","affiliations":[{"raw_affiliation_string":"Human Centered Design and Engineering, University of Washington, United States","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021329493","display_name":"Anhong Guo","orcid":"https://orcid.org/0000-0002-4447-7818"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I4210111179","display_name":"Michigan United","ror":"https://ror.org/0291ys696","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210111179"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anhong Guo","raw_affiliation_strings":["Computer Science and Engineering, University of Michigan, United States"],"raw_orcid":"https://orcid.org/0000-0002-4447-7818","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Michigan, United States","institution_ids":["https://openalex.org/I27837315","https://openalex.org/I4210111179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021329493"],"corresponding_institution_ids":["https://openalex.org/I27837315","https://openalex.org/I4210111179"],"apc_list":null,"apc_paid":null,"fwci":1.9046,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87259521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9764000177383423,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9595999717712402,"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":0.8141881823539734},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5378339290618896},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5350196361541748},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5309106111526489},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5062636137008667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5033969283103943},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4672790765762329},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4065665006637573},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.34198155999183655},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33389127254486084},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32483792304992676},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.059166401624679565}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141881823539734},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5378339290618896},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5350196361541748},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5309106111526489},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5062636137008667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5033969283103943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4672790765762329},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4065665006637573},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.34198155999183655},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33389127254486084},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32483792304992676},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.059166401624679565},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3663548.3675599","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3663548.3675599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 26th International ACM SIGACCESS Conference on Computers and Accessibility","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.06632","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.06632","pdf_url":"https://arxiv.org/pdf/2408.06632","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:deepblue.lib.umich.edu:2027.42/198548","is_oa":false,"landing_page_url":"https://hdl.handle.net/2027.42/198548","pdf_url":null,"source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.06632","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.06632","pdf_url":"https://arxiv.org/pdf/2408.06632","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402427035.pdf","grobid_xml":"https://content.openalex.org/works/W4402427035.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1990373827","https://openalex.org/W2035891484","https://openalex.org/W2090048052","https://openalex.org/W2124351162","https://openalex.org/W2289988710","https://openalex.org/W2406390611","https://openalex.org/W2578190051","https://openalex.org/W2588822708","https://openalex.org/W2772495254","https://openalex.org/W2791813490","https://openalex.org/W2916904544","https://openalex.org/W2941733318","https://openalex.org/W2995188596","https://openalex.org/W3095707999","https://openalex.org/W3095979162","https://openalex.org/W3116540451","https://openalex.org/W3121464409","https://openalex.org/W3162032064","https://openalex.org/W3163863570","https://openalex.org/W3206736270","https://openalex.org/W3207136799","https://openalex.org/W3207904152","https://openalex.org/W4221055872","https://openalex.org/W4224948613","https://openalex.org/W4224993535","https://openalex.org/W4225086399","https://openalex.org/W4225150333","https://openalex.org/W4225163156","https://openalex.org/W4226067028","https://openalex.org/W4281774797","https://openalex.org/W4307136517","https://openalex.org/W4307136540","https://openalex.org/W4307472449","https://openalex.org/W4309617590","https://openalex.org/W4312933868","https://openalex.org/W4322759491","https://openalex.org/W4366588993","https://openalex.org/W4366729076","https://openalex.org/W4385271134","https://openalex.org/W4385527149","https://openalex.org/W4386076215","https://openalex.org/W4387793507","https://openalex.org/W4387793554","https://openalex.org/W4387801394","https://openalex.org/W4388235266","https://openalex.org/W4390874575","https://openalex.org/W4396833066","https://openalex.org/W4403624885","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W4319453795","https://openalex.org/W4205104112","https://openalex.org/W1974870326","https://openalex.org/W2770776392","https://openalex.org/W3176454756","https://openalex.org/W2772330423","https://openalex.org/W3163523050","https://openalex.org/W3006381446","https://openalex.org/W4386301887","https://openalex.org/W3015353979"],"abstract_inverted_index":{"Image":[0],"editing":[1,19,24,59],"is":[2],"an":[3],"iterative":[4],"process":[5],"that":[6,55,161],"requires":[7],"precise":[8],"visual":[9,120,203],"evaluation":[10],"and":[11,36,84,101,124,127,138,167,180],"manipulation":[12],"for":[13,34,108],"the":[14,18,74,78,98,109,113,141,184,193],"output":[15],"to":[16,40,111,136,165,201],"match":[17],"intent.":[20],"However,":[21],"current":[22],"image":[23,58,79,99,169],"tools":[25],"do":[26],"not":[27],"provide":[28],"accessible":[29,61],"interaction":[30],"nor":[31],"sufficient":[32],"feedback":[33,107],"blind":[35,155],"low":[37],"vision":[38],"individuals":[39],"achieve":[41],"this":[42],"level":[43],"of":[44,105,119,187,195],"control.":[45],"To":[46],"address":[47],"this,":[48],"we":[49,159,191],"developed":[50],"EditScribe,":[51,73],"a":[52,117,151],"prototype":[53],"system":[54],"makes":[56],"object-level":[57],"actions":[60,90,171],"using":[62,91],"natural":[63,93,197],"language":[64,94,198],"verification":[65,106,144,188,199],"loops":[66,200],"powered":[67],"by":[68],"large":[69],"multimodal":[70],"models.":[71],"Using":[72],"user":[75,110,131],"first":[76],"comprehends":[77],"content":[80],"through":[81],"initial":[82],"general":[83,126],"object":[85,128],"descriptions,":[86],"then":[87],"specifies":[88],"edit":[89,170],"open-ended":[92],"prompts.":[95],"EditScribe":[96,162],"performs":[97],"edit,":[100,115],"provides":[102],"four":[103],"types":[104,186],"verify":[112,168],"performed":[114],"including":[116],"summary":[118],"changes,":[121],"AI":[122],"judgement,":[123],"updated":[125],"descriptions.":[129],"The":[130],"can":[132],"ask":[133],"follow-up":[134],"questions":[135],"clarify":[137],"probe":[139],"into":[140],"edits":[142],"or":[143,156],"feedback,":[145],"before":[146],"performing":[147],"another":[148],"edit.":[149],"In":[150],"study":[152],"with":[153],"ten":[154],"low-vision":[157],"users,":[158],"found":[160],"supported":[163],"participants":[164],"perform":[166],"non-visually.":[172],"We":[173],"observed":[174],"different":[175],"prompting":[176],"strategies":[177],"from":[178],"participants,":[179],"their":[181],"perceptions":[182],"on":[183],"various":[185],"feedback.":[189],"Finally,":[190],"discuss":[192],"implications":[194],"leveraging":[196],"make":[202],"authoring":[204],"non-visually":[205],"accessible.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2024-09-11T00:00:00"}
