{"id":"https://openalex.org/W3191804539","doi":"https://doi.org/10.24963/ijcai.2021/235","title":"UIBert: Learning Generic Multimodal Representations for UI Understanding","display_name":"UIBert: Learning Generic Multimodal Representations for UI Understanding","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3191804539","doi":"https://doi.org/10.24963/ijcai.2021/235","mag":"3191804539"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/235","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/235","pdf_url":"https://www.ijcai.org/proceedings/2021/0235.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0235.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033952401","display_name":"Chongyang Bai","orcid":"https://orcid.org/0000-0002-1245-9877"},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]},{"id":"https://openalex.org/I4210166639","display_name":"Dartmouth Hospital","ror":"https://ror.org/02j3qj605","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I4210166639"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Chongyang Bai","raw_affiliation_strings":["Dartmouth College"],"affiliations":[{"raw_affiliation_string":"Dartmouth College","institution_ids":["https://openalex.org/I4210166639","https://openalex.org/I107672454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049537668","display_name":"Xiaoxue Zang","orcid":"https://orcid.org/0000-0002-5923-3429"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoxue Zang","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652479","display_name":"Ying Xu","orcid":"https://orcid.org/0000-0003-0904-1477"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Xu","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070178342","display_name":"Srinivas Sunkara","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Sunkara","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087687501","display_name":"Abhinav Rastogi","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Rastogi","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101933321","display_name":"Jindong Chen","orcid":"https://orcid.org/0000-0002-5560-1431"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jindong Chen","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044698998","display_name":"Blaise Ag\u00fcera y Arcas","orcid":"https://orcid.org/0000-0003-2256-9823"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Blaise Ag\u00fcera y Arcas","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5033952401"],"corresponding_institution_ids":["https://openalex.org/I107672454","https://openalex.org/I4210166639"],"apc_list":null,"apc_paid":null,"fwci":1.7676,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87521902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1705","last_page":"1712"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.988099992275238,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8640668392181396},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7068926095962524},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5961225032806396},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.4842776656150818},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.42746907472610474},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4198572337627411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4050515592098236},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37214213609695435},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33934342861175537},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17015770077705383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8640668392181396},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7068926095962524},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5961225032806396},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.4842776656150818},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.42746907472610474},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4198572337627411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4050515592098236},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37214213609695435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33934342861175537},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17015770077705383},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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:10.24963/ijcai.2021/235","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/235","pdf_url":"https://www.ijcai.org/proceedings/2021/0235.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/235","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/235","pdf_url":"https://www.ijcai.org/proceedings/2021/0235.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3191804539.pdf","grobid_xml":"https://content.openalex.org/works/W3191804539.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1924770834","https://openalex.org/W2187089797","https://openalex.org/W2259472270","https://openalex.org/W2525778437","https://openalex.org/W2896017593","https://openalex.org/W2896457183","https://openalex.org/W2897966957","https://openalex.org/W2916286502","https://openalex.org/W2955425717","https://openalex.org/W2969876226","https://openalex.org/W2996428491","https://openalex.org/W2998356391","https://openalex.org/W3034392229","https://openalex.org/W3101041928","https://openalex.org/W3103843169","https://openalex.org/W3116323972","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248","https://openalex.org/W2768810474"],"abstract_inverted_index":{"To":[0,64],"improve":[1],"the":[2,102,111,144],"accessibility":[3],"of":[4,116,121,135],"smart":[5],"devices":[6],"and":[7,19,49,52,94,113,139],"to":[8,22,39,54,86,165],"simplify":[9],"their":[10,24],"usage,":[11],"building":[12],"models":[13],"which":[14],"understand":[15],"user":[16],"interfaces":[17],"(UIs)":[18],"assist":[20],"users":[21],"complete":[23],"tasks":[25,80,128,156],"is":[26,62,100],"critical.":[27],"However,":[28],"unique":[29],"challenges":[30,67],"are":[31,108,119],"proposed":[32],"by":[33,163],"UI-specific":[34],"characteristics,":[35],"such":[36,66],"as":[37],"how":[38,53],"effectively":[40],"leverage":[41],"multimodal":[42,161],"UI":[43,84,93,107,117,137,155],"features":[44,104,115,134],"that":[45,101],"involve":[46],"image,":[47],"text,":[48],"structural":[50],"metadata":[51],"achieve":[55],"good":[56],"performance":[57],"when":[58],"high-quality":[59],"labeled":[60],"data":[61,85],"unavailable.":[63],"address":[65],"we":[68],"introduce":[69],"UIBert,":[70],"a":[71,92,106,136],"transformer-based":[72],"joint":[73],"image-text":[74],"model":[75],"trained":[76],"through":[77],"novel":[78],"pre-training":[79],"on":[81,151],"large-scale":[82],"unlabeled":[83],"learn":[87],"generic":[88],"feature":[89],"representations":[90],"for":[91],"its":[95],"components.":[96],"Our":[97],"key":[98],"intuition":[99],"heterogeneous":[103],"in":[105,143],"self-aligned,":[109],"i.e.,":[110],"image":[112],"text":[114],"components,":[118],"predictive":[120],"each":[122],"other.":[123],"We":[124,147],"propose":[125],"five":[126],"pretraining":[127],"utilizing":[129],"this":[130],"self-alignment":[131],"among":[132],"different":[133],"component":[138],"across":[140],"various":[141],"components":[142],"same":[145],"UI.":[146],"evaluate":[148],"our":[149],"method":[150],"nine":[152],"real-world":[153],"downstream":[154],"where":[157],"UIBert":[158],"outperforms":[159],"strong":[160],"baselines":[162],"up":[164],"9.26%":[166],"accuracy.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}