{"id":"https://openalex.org/W3136154081","doi":"https://doi.org/10.1145/3451340","title":"Learning Multimodal Affinities for Textual Editing in Images","display_name":"Learning Multimodal Affinities for Textual Editing in Images","publication_year":2021,"publication_date":"2021-06-30","ids":{"openalex":"https://openalex.org/W3136154081","doi":"https://doi.org/10.1145/3451340","mag":"3136154081"},"language":"en","primary_location":{"id":"doi:10.1145/3451340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3451340","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.10139","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Or Perel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Or Perel","raw_affiliation_strings":["Amazon Web Services, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Israel","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Oron Anschel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oron Anschel","raw_affiliation_strings":["Amazon Web Services, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Israel","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Omri Ben-Eliezer","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omri Ben-Eliezer","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shai Mazor","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shai Mazor","raw_affiliation_strings":["Amazon Web Services, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Israel","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Hadar Averbuch-Elor","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hadar Averbuch-Elor","raw_affiliation_strings":["Cornell-Tech, Cornell University, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell-Tech, Cornell University, NY","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0941,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33928482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"40","issue":"3","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8438000082969666,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8438000082969666,"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":0.05420000106096268,"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":0.038600001484155655,"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/semantics","display_name":"Semantics (computer science)","score":0.6182000041007996},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5778999924659729},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5627999901771545},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5609999895095825},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5327000021934509},{"id":"https://openalex.org/keywords/affinities","display_name":"Affinities","score":0.5069000124931335},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4968000054359436},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.4693000018596649}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220000267028809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6273000240325928},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6182000041007996},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5778999924659729},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5627999901771545},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5609999895095825},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5327000021934509},{"id":"https://openalex.org/C2780283098","wikidata":"https://www.wikidata.org/wiki/Q4688960","display_name":"Affinities","level":2,"score":0.5069000124931335},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.4693000018596649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4438000023365021},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.32910001277923584},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3133000135421753},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.27970001101493835},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3451340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3451340","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2103.10139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.10139","pdf_url":"https://arxiv.org/pdf/2103.10139","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.10139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.10139","pdf_url":"https://arxiv.org/pdf/2103.10139","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1922126009","https://openalex.org/W1933349210","https://openalex.org/W1975679132","https://openalex.org/W1983764898","https://openalex.org/W1994456831","https://openalex.org/W2015141245","https://openalex.org/W2048060845","https://openalex.org/W2072393922","https://openalex.org/W2117493512","https://openalex.org/W2124410444","https://openalex.org/W2131054109","https://openalex.org/W2135164809","https://openalex.org/W2148520845","https://openalex.org/W2194775991","https://openalex.org/W2307512708","https://openalex.org/W2475287302","https://openalex.org/W2481240925","https://openalex.org/W2508429489","https://openalex.org/W2608862709","https://openalex.org/W2725765016","https://openalex.org/W2792861137","https://openalex.org/W2962852342","https://openalex.org/W2963644680","https://openalex.org/W2966386095","https://openalex.org/W2997095758","https://openalex.org/W3016211260","https://openalex.org/W3029772237","https://openalex.org/W4236981415","https://openalex.org/W4243327725","https://openalex.org/W4249710618"],"related_works":[],"abstract_inverted_index":{"Nowadays,":[0],"as":[1],"cameras":[2],"are":[3,13],"rapidly":[4],"adopted":[5],"in":[6,55,87,119],"our":[7,97,135],"daily":[8],"routine,":[9],"images":[10,21,142],"of":[11,31,64,96,123,147,163],"documents":[12,148],"becoming":[14],"both":[15],"abundant":[16],"and":[17,36,68,114,149,161],"prevalent.":[18],"Unlike":[19],"natural":[20],"that":[22,112,134],"capture":[23],"physical":[24],"objects,":[25],"document-images":[26],"contain":[27],"a":[28,44,56,100,144],"significant":[29],"amount":[30],"text":[32],"with":[33],"critical":[34],"semantics":[35],"complicated":[37],"layouts.":[38],"In":[39],"this":[40],"work,":[41],"we":[42],"devise":[43],"generic":[45],"unsupervised":[46],"technique":[47,136],"to":[48,81,127],"learn":[49,129],"multimodal":[50,121],"affinities":[51,80],"between":[52],"textual":[53,85,125],"entities":[54,86],"document-image,":[57],"considering":[58],"their":[59,65,69],"visual":[60],"style,":[61],"the":[62,73,84,88,110,120,124,130,158,164],"content":[63],"underlying":[66],"text,":[67],"geometric":[70],"context":[71],"within":[72],"image.":[74,165],"We":[75,132],"then":[76],"use":[77],"these":[78],"learned":[79],"automatically":[82],"cluster":[83],"image":[89,107],"into":[90],"different":[91],"semantic":[92],"groups.":[93],"The":[94],"core":[95],"approach":[98],"is":[99],"deep":[101],"optimization":[102],"scheme":[103],"dedicated":[104],"for":[105,153],"an":[106],"provided":[108],"by":[109],"user":[111],"detects":[113],"leverages":[115],"reliable":[116],"pairwise":[117],"connections":[118],"representation":[122],"elements":[126],"properly":[128],"affinities.":[131],"show":[133],"can":[137],"operate":[138],"on":[139],"highly":[140],"varying":[141],"spanning":[143],"wide":[145],"range":[146],"demonstrate":[150],"its":[151],"applicability":[152],"various":[154],"editing":[155],"operations":[156],"manipulating":[157],"content,":[159],"appearance,":[160],"geometry":[162]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2021-03-29T00:00:00"}