{"id":"https://openalex.org/W7125905763","doi":"https://doi.org/10.1109/smc58881.2025.11342912","title":"MMNet: A Multi-Scale Multimodal Model for End-to-End Grouping of Fragmented UI Elements","display_name":"MMNet: A Multi-Scale Multimodal Model for End-to-End Grouping of Fragmented UI Elements","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125905763","doi":"https://doi.org/10.1109/smc58881.2025.11342912"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124083717","display_name":"Liuzhou Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liuzhou Zhang","raw_affiliation_strings":["Central China Normal University,School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central China Normal University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113408366","display_name":"Yuanlei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanlei Wang","raw_affiliation_strings":["Hunan University,College of Computer Science & Electronic Engineering,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science & Electronic Engineering,Changsha,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101665660","display_name":"Yuqi Zhao","orcid":"https://orcid.org/0000-0002-2642-5109"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Zhao","raw_affiliation_strings":["Central China Normal University,School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central China Normal University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123712855","display_name":"Shuangshuang Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuangshuang Tian","raw_affiliation_strings":["Central China Normal University,School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central China Normal University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I40963666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64462346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6905","last_page":"6910"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.4643999934196472,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10789","display_name":"Interactive and Immersive Displays","score":0.4643999934196472,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10803","display_name":"Innovative Human-Technology Interaction","score":0.06830000132322311,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.0494999997317791,"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/representation","display_name":"Representation (politics)","score":0.5616000294685364},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5600000023841858},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5436999797821045},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4487999975681305},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4447999894618988},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.43220001459121704},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4300999939441681},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4131999909877777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199999928474426},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5616000294685364},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5600000023841858},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5436999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4902999997138977},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.43220001459121704},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3521000146865845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33239999413490295},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2727000117301941},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6646842956542969,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W3138516171","https://openalex.org/W3163374010","https://openalex.org/W4250482878","https://openalex.org/W4360994979","https://openalex.org/W4366549916","https://openalex.org/W4386876193","https://openalex.org/W4402753874"],"related_works":[],"abstract_inverted_index":{"Graphical":[0],"User":[1],"Interface":[2],"(GUI)":[3],"designs":[4],"often":[5],"result":[6],"in":[7],"fragmented":[8,30,81],"elements,":[9,31,144],"leading":[10],"to":[11,40,59,113,128],"inefficient":[12],"and":[13,36,54,69,90,155,160],"redundant":[14],"code":[15,159],"when":[16],"automatically":[17],"converted.":[18],"This":[19,64],"paper":[20],"presents":[21],"MMNet,":[22],"a":[23,55,61,87,124],"novel":[24],"end-to-end":[25],"model":[26],"for":[27,111],"grouping":[28,42],"these":[29],"leveraging":[32],"multimodal":[33,52,73],"feature":[34],"representations":[35],"advanced":[37,96],"retention":[38,57,126],"mechanisms":[39],"improve":[41],"accuracy.":[43],"MMNet":[44,145],"uses":[45],"UI":[46,62,82,105,135,143],"sequence":[47],"prediction,":[48],"enhanced":[49],"by":[50],"large":[51,98],"models,":[53],"multi-scale":[56,70,125],"mechanism":[58,127],"build":[60],"encoder.":[63],"approach":[65],"captures":[66],"temporal":[67],"dependencies":[68],"features,":[71],"improving":[72],"representation":[74],"learning.":[75],"To":[76],"address":[77],"the":[78,101,116,131],"lack":[79],"of":[80,104,141],"element":[83],"datasets,":[84],"we":[85],"constructed":[86],"new":[88],"dataset":[89,140],"enriched":[91],"its":[92,153],"visual":[93],"information":[94],"using":[95],"multi-modal":[97],"models.":[99],"Given":[100],"complex":[102],"nature":[103],"design":[106],"prototypes,":[107],"it":[108],"remains":[109],"challenging":[110],"models":[112],"effectively":[114],"learn":[115],"relationships":[117],"between":[118,134],"different":[119],"modalities.":[120],"We":[121],"have":[122],"adopted":[123],"further":[129],"refine":[130],"relationship":[132],"modeling":[133],"elements.":[136],"Evaluated":[137],"on":[138],"our":[139],"71,851":[142],"outperformed":[146],"three":[147],"state-of-the-art":[148],"deep":[149],"learning":[150],"methods,":[151],"demonstrating":[152],"effectiveness":[154],"innovation.":[156],"The":[157],"open-source":[158],"datasets":[161],"are":[162],"available":[163],"at":[164],"https://anonymous.4open.science/r/MMNet-2343.":[165]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-29T00:00:00"}