{"id":"https://openalex.org/W4404545083","doi":"https://doi.org/10.1007/978-3-031-73113-6_10","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","display_name":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","publication_year":2024,"publication_date":"2024-11-20","ids":{"openalex":"https://openalex.org/W4404545083","doi":"https://doi.org/10.1007/978-3-031-73113-6_10"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-73113-6_10","doi":"https://doi.org/10.1007/978-3-031-73113-6_10","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-73113-6_10","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W4404545406","display_name":"Computer Vision \u2013 ECCV 2024"},"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.17553","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089262860","display_name":"Raghav Kapoor","orcid":"https://orcid.org/0000-0002-1030-7423","observed_orcids":["https://orcid.org/0000-0002-1030-7423"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Raghav Kapoor","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082028744","display_name":"Yash Butala","orcid":"https://orcid.org/0000-0002-5999-0702","observed_orcids":["https://orcid.org/0000-0002-5999-0702"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yash Parag Butala","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028563651","display_name":"Melisa Russak","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Melisa Russak","raw_affiliation_strings":["Writer.com, San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Writer.com, San Francisco, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009550511","display_name":"Jing Yu Koh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Yu Koh","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053209482","display_name":"Kiran P. Kamble","orcid":"https://orcid.org/0000-0002-9133-7826","observed_orcids":["https://orcid.org/0000-0002-9133-7826"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiran Kamble","raw_affiliation_strings":["Writer.com, San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Writer.com, San Francisco, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092442112","display_name":"Waseem AlShikh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Waseem AlShikh","raw_affiliation_strings":["Writer.com, San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Writer.com, San Francisco, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071983998","display_name":"Ruslan Salakhutdinov","orcid":"https://orcid.org/0000-0002-3752-2756","observed_orcids":["https://orcid.org/0000-0002-3752-2756"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruslan Salakhutdinov","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089262860"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":13.0336,"has_fulltext":true,"cited_by_count":93,"citation_normalized_percentile":{"value":0.9902053,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5121999979019165,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5121999979019165,"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/T12031","display_name":"Speech and dialogue systems","score":0.11659999936819077,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.043699998408555984,"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/browser-automation","display_name":"browser automation","score":0.5659999847412109},{"id":"https://openalex.org/keywords/multimodal-language-models","display_name":"multimodal language models","score":0.675000011920929},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.7730000019073486},{"id":"https://openalex.org/keywords/gpt-4","display_name":"GPT-4","score":0.7200000286102295},{"id":"https://openalex.org/keywords/human-computer-interaction","display_name":"human-computer interaction","score":0.6930000185966492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8919274806976318},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.830132246017456},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49226394295692444},{"id":"https://openalex.org/C45371612","wikidata":"https://www.wikidata.org/wiki/Q3058587","display_name":"Generalist and specialist species","level":3,"score":0.43895310163497925},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3634655177593231},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3358616232872009},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3343769609928131},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06909960508346558},{"id":"https://openalex.org/C185933670","wikidata":"https://www.wikidata.org/wiki/Q52105","display_name":"Habitat","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-031-73113-6_10","doi":"https://doi.org/10.1007/978-3-031-73113-6_10","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-73113-6_10","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2402.17553","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.17553","pdf_url":"https://arxiv.org/pdf/2402.17553","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.17553","doi":"https://doi.org/10.48550/arxiv.2402.17553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.17553","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.17553","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.17553","pdf_url":"https://arxiv.org/pdf/2402.17553","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404545083.pdf","grobid_xml":"https://content.openalex.org/works/W4404545083.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2133665775","https://openalex.org/W2765874585","https://openalex.org/W3034392229","https://openalex.org/W3089307846","https://openalex.org/W3101041928","https://openalex.org/W3116323972","https://openalex.org/W3121976951","https://openalex.org/W3167070827","https://openalex.org/W3191804539","https://openalex.org/W3206316161","https://openalex.org/W4225784175","https://openalex.org/W4226227340","https://openalex.org/W4322718191","https://openalex.org/W4362515116","https://openalex.org/W4377372292","https://openalex.org/W4379929801","https://openalex.org/W4380994269","https://openalex.org/W4385262076","https://openalex.org/W4385327683","https://openalex.org/W4385574233","https://openalex.org/W4385574370","https://openalex.org/W4385682136","https://openalex.org/W4386065691","https://openalex.org/W4386185625","https://openalex.org/W4387294588","https://openalex.org/W4389520251","https://openalex.org/W4389524484","https://openalex.org/W4390041933","https://openalex.org/W4390872747","https://openalex.org/W4390874575","https://openalex.org/W4393065402","https://openalex.org/W4402667024","https://openalex.org/W4402670435","https://openalex.org/W4402727764","https://openalex.org/W4404356490","https://openalex.org/W6603135882","https://openalex.org/W6725763299","https://openalex.org/W6941483331","https://openalex.org/W6989086347","https://openalex.org/W7133210150","https://openalex.org/W7133215859","https://openalex.org/W7133217858","https://openalex.org/W7133224230"],"related_works":["https://openalex.org/W4415797693","https://openalex.org/W4399598135","https://openalex.org/W7106817146","https://openalex.org/W4404307593","https://openalex.org/W7162892933","https://openalex.org/W4391244971","https://openalex.org/W4401024359","https://openalex.org/W4416025490","https://openalex.org/W7155584115","https://openalex.org/W4417137026"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":36},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":21}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-11-21T00:00:00"}
