{"id":"https://openalex.org/W4415539539","doi":"https://doi.org/10.1145/3746027.3755688","title":"ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use","display_name":"ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539539","doi":"https://doi.org/10.1145/3746027.3755688"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755688","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755688","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755688","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069234886","display_name":"K.-J. Li","orcid":"https://orcid.org/0009-0007-9842-3552"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kaixin Li","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0007-9842-3552","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziyang Meng","orcid":"https://orcid.org/0009-0001-5379-8461"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Meng","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-5379-8461","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078451082","display_name":"Hongzhan Lin","orcid":"https://orcid.org/0000-0002-4111-8334"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongzhan Lin","raw_affiliation_strings":["Hong Kong Baptist University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-4111-8334","affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055657033","display_name":"Ziyang Luo","orcid":"https://orcid.org/0000-0002-6037-0471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyang Luo","raw_affiliation_strings":["Salesforce Research, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-6037-0471","affiliations":[{"raw_affiliation_string":"Salesforce Research, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuchen Tian","orcid":"https://orcid.org/0009-0000-1437-0270"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuchen Tian","raw_affiliation_strings":["Hong Kong Baptist University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0000-1437-0270","affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034823980","display_name":"Jing Ma","orcid":"https://orcid.org/0000-0002-7464-8331"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Ma","raw_affiliation_strings":["Hong Kong Baptist University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-7464-8331","affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102956977","display_name":"Zhiyong Huang","orcid":"https://orcid.org/0000-0002-1931-7775"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiyong Huang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1931-7775","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8778","last_page":"8786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.41449999809265137,"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/T10799","display_name":"Data Visualization and Analytics","score":0.41449999809265137,"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/T10648","display_name":"Virtual Reality Applications and Impacts","score":0.35910001397132874,"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/T10731","display_name":"Educational Games and Gamification","score":0.33149999380111694,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.737500011920929},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7049999833106995},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.621399998664856},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6064000129699707},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.5266000032424927},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.38089999556541443},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.37860000133514404},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.336899995803833}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.737500011920929},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7049999833106995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6862000226974487},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.621399998664856},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6064000129699707},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5440999865531921},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4068000018596649},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C544833334","wikidata":"https://www.wikidata.org/wiki/Q2005","display_name":"JavaScript","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3140000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3077999949455261},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C545109879","wikidata":"https://www.wikidata.org/wiki/Q5157412","display_name":"Computer Applications","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755688","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755688","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755688","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755688","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W4402671607","https://openalex.org/W4402727764","https://openalex.org/W4403888362","https://openalex.org/W4404782300"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,13,31,76],"Multi-modal":[3],"Large":[4],"Language":[5],"Models":[6],"(MLLMs)":[7],"have":[8],"led":[9],"to":[10,54,68,153],"significant":[11],"progress":[12],"developing":[14],"GUI":[15,43,107,147,179],"agents":[16,180],"for":[17,42,181],"general":[18],"tasks":[19],"such":[20],"as":[21],"web":[22],"browsing":[23],"and":[24,49,102,172],"mobile":[25],"phone":[26],"use.":[27],"However,":[28],"their":[29],"application":[30],"professional":[32,78,90,182],"domains":[33,91],"remains":[34],"under-explored.":[35],"These":[36],"specialized":[37],"workflows":[38],"introduce":[39,62],"unique":[40],"challenges":[41],"perception":[44],"models,":[45],"including":[46],"high-resolution":[47,77,84],"displays":[48],"complex":[50],"environments":[51],"which":[52],"lead":[53],"smaller":[55],"target":[56],"sizes.":[57],"In":[58],"this":[59,113,135],"paper,":[60],"we":[61,137],"ScreenSpot-Pro,":[63],"a":[64,87,140,150,155],"new":[65],"benchmark":[66,81,171],"designed":[67],"rigorously":[69],"evaluate":[70],"the":[71,116,128,146,176],"grounding":[72,108],"capabilities":[73],"of":[74,89,149,178],"MLLMs":[75],"settings.":[79,183],"The":[80],"comprises":[82],"authentic":[83],"images":[85],"from":[86],"variety":[88],"with":[92,115,161],"expert":[93],"annotations.":[94],"It":[95],"spans":[96],"23":[97],"applications":[98],"across":[99],"five":[100],"industries":[101],"three":[103],"operating":[104],"systems.":[105],"Existing":[106],"models":[109],"perform":[110],"poorly":[111],"on":[112,134],"dataset,":[114],"best":[117],"model":[118],"achieving":[119,158],"only":[120],"18.9%.":[121],"Our":[122],"experiments":[123],"reveal":[124],"that":[125,144,169],"strategically":[126],"reducing":[127],"search":[129,142],"area":[130],"enhances":[131],"accuracy.":[132],"Based":[133],"insight,":[136],"propose":[138],"ScreenSeekeR,":[139],"visual":[141],"method":[143],"utilizes":[145],"knowledge":[148],"strong":[151],"planner":[152],"guide":[154],"cascaded":[156],"search,":[157],"state-of-the-art":[159],"performance":[160],"48.1%":[162],"without":[163],"any":[164],"additional":[165],"training.":[166],"We":[167],"hope":[168],"our":[170],"findings":[173],"will":[174],"advance":[175],"development":[177]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
