{"id":"https://openalex.org/W7171935224","doi":"https://doi.org/10.1145/3774521.3774535","title":"Screen2UI: Pixel-Only On-Device UI Hierarchy Generation","display_name":"Screen2UI: Pixel-Only On-Device UI Hierarchy Generation","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7171935224","doi":"https://doi.org/10.1145/3774521.3774535"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774535","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774535","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/10.1145/3774521.3774535","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134174255","display_name":"Anup Kushwaha","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anup Kushwaha","raw_affiliation_strings":["Samsung R&amp;D Institute Bangalore, Bengaluru, India"],"raw_orcid":"https://orcid.org/0009-0003-5091-0897","affiliations":[{"raw_affiliation_string":"Samsung R&amp;D Institute Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144149491","display_name":"Banseedhar Gondaliya","orcid":"https://orcid.org/0009-0001-7787-9186"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Banseedhar Gondaliya","raw_affiliation_strings":["Samsung R&amp;D Institute Bangalore, Bengaluru, India"],"raw_orcid":"https://orcid.org/0009-0001-7787-9186","affiliations":[{"raw_affiliation_string":"Samsung R&amp;D Institute Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073731888","display_name":"Chandramouli Sanchi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chandramouli Sanchi","raw_affiliation_strings":["Samsung R&amp;D Institute Bangalore, Bengaluru, India"],"raw_orcid":"https://orcid.org/0009-0002-9348-1685","affiliations":[{"raw_affiliation_string":"Samsung R&amp;D Institute Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144094402","display_name":"Surya Kumar","orcid":"https://orcid.org/0009-0004-0339-6386"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Surya Kumar","raw_affiliation_strings":["Samsung R&amp;D Institute Bangalore, Bengaluru, India"],"raw_orcid":"https://orcid.org/0009-0004-0339-6386","affiliations":[{"raw_affiliation_string":"Samsung R&amp;D Institute Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057881155","display_name":"Apil Thapa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Apil Thapa","raw_affiliation_strings":["Samsung R&amp;D Institute Bangalore, Bengaluru, India"],"raw_orcid":"https://orcid.org/0009-0007-3306-5125","affiliations":[{"raw_affiliation_string":"Samsung R&amp;D Institute Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5144109433","display_name":"Edula Sri Ranga Srihit Reddy","orcid":"https://orcid.org/0009-0003-2016-7553"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Edula Sri Ranga Srihit Reddy","raw_affiliation_strings":["Samsung R&amp;D Institute Bangalore, Bengaluru, India"],"raw_orcid":"https://orcid.org/0009-0003-2016-7553","affiliations":[{"raw_affiliation_string":"Samsung R&amp;D Institute Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210139030"],"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/json","display_name":"JSON","score":0.54339998960495},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5070000290870667},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5023999810218811},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.490200012922287},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4018999934196472},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.3926999866962433},{"id":"https://openalex.org/keywords/icon","display_name":"Icon","score":0.328000009059906},{"id":"https://openalex.org/keywords/android","display_name":"Android (operating system)","score":0.3190999925136566},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.3163999915122986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8208000063896179},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.54339998960495},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41749998927116394},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C2778447006","wikidata":"https://www.wikidata.org/wiki/Q1156474","display_name":"Icon","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C557433098","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android (operating system)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3066999912261963},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C2777080924","wikidata":"https://www.wikidata.org/wiki/Q334667","display_name":"Storyboard","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29750001430511475},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C17305859","wikidata":"https://www.wikidata.org/wiki/Q382944","display_name":"Soar","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2597000002861023},{"id":"https://openalex.org/C202477664","wikidata":"https://www.wikidata.org/wiki/Q1352449","display_name":"Client-side","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774535","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774535","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:10.1145/3774521.3774535","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774535","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":12,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2765874585","https://openalex.org/W2916286502","https://openalex.org/W2963163009","https://openalex.org/W2997747012","https://openalex.org/W3160022552","https://openalex.org/W3163374010","https://openalex.org/W3199730823","https://openalex.org/W4224981985","https://openalex.org/W4225089191","https://openalex.org/W4312443924","https://openalex.org/W4408615011"],"related_works":[],"abstract_inverted_index":{"Mobile":[0],"apps":[1],"often":[2],"expose":[3],"limited":[4],"or":[5,196],"missing":[6],"accessibility":[7,97],"metadata,":[8],"making":[9],"it":[10,127],"hard":[11],"for":[12,96,153,170],"assistive":[13],"technologies":[14],"and":[15,20,72,84,98,118,131,180,188],"automation":[16],"tools":[17],"to":[18,89],"understand":[19],"operate":[21],"user":[22],"interfaces.":[23],"We":[24,77],"present":[25],"Screen2UI,":[26],"an":[27,181],"on-device":[28,171],"system":[29],"that":[30,185],"reconstructs":[31],"a":[32,38,45,51,56,91,101,139,154,158,166,174],"structured":[33],"UI":[34,62,172],"hierarchy":[35,177],"directly":[36],"from":[37],"screenshot.":[39],"At":[40],"its":[41],"core":[42],"is":[43],"MSM-Net,":[44],"unified,":[46],"multi-task":[47],"detector":[48],"built":[49],"on":[50,138],"YOLO11":[52],"backbone":[53],"that,":[54],"in":[55,134],"single":[57],"pass,":[58],"(i)":[59],"localizes":[60],"11":[61],"element":[63,75],"types,":[64],"(ii)":[65],"assigns":[66],"fine-grained":[67],"icon":[68,114],"semantics":[69],"(145":[70],"classes),":[71],"(iii)":[73],"predicts":[74],"tappability.":[76],"fuse":[78],"these":[79],"predictions":[80],"with":[81,157],"OCR":[82],"text":[83],"apply":[85],"lightweight":[86],"containment":[87],"heuristics":[88],"produce":[90],"JSON":[92],"view":[93],"tree":[94],"suitable":[95],"automation.":[99],"On":[100,123],"held-out":[102],"test":[103],"set":[104],"of":[105,112,116,121],"15k":[106],"screens,":[107],"MSM-Net":[108],"attains":[109],"[email":[110],"protected]":[111],"86.4%,":[113],"Top-1":[115],"91.2%,":[117],"tappability":[119],"F1":[120],"91.5%.":[122],"the":[124],"VINS":[125],"benchmark,":[126],"surpasses":[128],"published":[129],"SSD":[130],"YOLOv5s":[132],"baselines":[133],"mean":[135],"AP.":[136],"Deployed":[137],"Samsung":[140],"Galaxy":[141],"S25":[142],"(Snapdragon":[143],"8":[144],"Elite),":[145],"Screen2UI":[146],"achieves":[147],"600ms":[148],"per":[149],"screen":[150],"(vs.":[151,162],"900ms":[152],"multi-model":[155],"pipeline)":[156],"10.2M":[159],"parameter":[160],"model":[161,169],"15.1M).":[163],"Contributions":[164],"are:":[165],"compact":[167],"unified":[168],"understanding;":[173],"fast,":[175],"deterministic":[176],"reconstruction":[178],"procedure;":[179],"empirical":[182],"study":[183],"showing":[184],"multitask":[186],"learning":[187],"synthetic":[189],"augmentation":[190],"improve":[191],"accuracy":[192],"without":[193],"sacrificing":[194],"latency":[195],"footprint.":[197]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}
