{"id":"https://openalex.org/W4403888851","doi":"https://doi.org/10.1007/978-3-031-73039-9_4","title":"MEERKAT: Audio-Visual Large Language Model for\u00a0Grounding in\u00a0Space and\u00a0Time","display_name":"MEERKAT: Audio-Visual Large Language Model for\u00a0Grounding in\u00a0Space and\u00a0Time","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403888851","doi":"https://doi.org/10.1007/978-3-031-73039-9_4"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-73039-9_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-73039-9_4","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,"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"},"type":"book-chapter","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/A5101778650","display_name":"Sanjoy Chowdhury","orcid":"https://orcid.org/0000-0003-4256-4720"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sanjoy Chowdhury","raw_affiliation_strings":["University of Maryland, College Park, Maryland, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, Maryland, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977185","display_name":"Sayan Nag","orcid":"https://orcid.org/0000-0001-5652-125X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sayan Nag","raw_affiliation_strings":["University of Toronto, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084391740","display_name":"Subhrajyoti Dasgupta","orcid":"https://orcid.org/0009-0000-7582-4547"},"institutions":[{"id":"https://openalex.org/I4210156952","display_name":"Malaysia Theological Seminary","ror":"https://ror.org/05jhctt84","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210156952"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Subhrajyoti Dasgupta","raw_affiliation_strings":["Mila and Universit\u00e9 de Montr\u00e9al, Negeri Sembilan, Malaysia"],"affiliations":[{"raw_affiliation_string":"Mila and Universit\u00e9 de Montr\u00e9al, Negeri Sembilan, Malaysia","institution_ids":["https://openalex.org/I4210156952"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450148","display_name":"Jun Chen","orcid":"https://orcid.org/0000-0001-8883-0970"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Jun Chen","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085089542","display_name":"Mohamed Elhoseiny","orcid":"https://orcid.org/0000-0001-9659-1551"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohamed Elhoseiny","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102907601","display_name":"Ruohan Gao","orcid":"https://orcid.org/0000-0002-8346-1114"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruohan Gao","raw_affiliation_strings":["University of Maryland, College Park, Maryland, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, Maryland, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland, College Park, Maryland, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, Maryland, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101778650"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":3.6512,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94837884,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9717000126838684,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8227648735046387},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.745686948299408},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5208871364593506},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4696948528289795},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41557061672210693},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4057163596153259},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.20771196484565735},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.17909970879554749},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0943635106086731},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06177562475204468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8227648735046387},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.745686948299408},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5208871364593506},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4696948528289795},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41557061672210693},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4057163596153259},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.20771196484565735},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.17909970879554749},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0943635106086731},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06177562475204468}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-73039-9_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-73039-9_4","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,"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W2037227137","https://openalex.org/W2593116425","https://openalex.org/W2931433835","https://openalex.org/W2963680395","https://openalex.org/W2964109005","https://openalex.org/W2980339970","https://openalex.org/W2981852735","https://openalex.org/W3012255272","https://openalex.org/W3015371781","https://openalex.org/W3090449556","https://openalex.org/W3118120400","https://openalex.org/W3135367836","https://openalex.org/W3170088426","https://openalex.org/W3206634578","https://openalex.org/W4214604251","https://openalex.org/W4225323055","https://openalex.org/W4226278401","https://openalex.org/W4283009931","https://openalex.org/W4283709432","https://openalex.org/W4288083516","https://openalex.org/W4296605665","https://openalex.org/W4304098310","https://openalex.org/W4312380001","https://openalex.org/W4312653918","https://openalex.org/W4312956471","https://openalex.org/W4313123347","https://openalex.org/W4319299730","https://openalex.org/W4372266552","https://openalex.org/W4372267673","https://openalex.org/W4377164404","https://openalex.org/W4384918448","https://openalex.org/W4385570984","https://openalex.org/W4386075532","https://openalex.org/W4386113246","https://openalex.org/W4389519587","https://openalex.org/W4389523744","https://openalex.org/W4390872419","https://openalex.org/W4390874283","https://openalex.org/W4392909577","https://openalex.org/W4394592978","https://openalex.org/W4394625659","https://openalex.org/W4402671548","https://openalex.org/W4402727272","https://openalex.org/W4402728164","https://openalex.org/W4402754134","https://openalex.org/W4404654668","https://openalex.org/W6600008909","https://openalex.org/W6600140940","https://openalex.org/W6600171454","https://openalex.org/W6600574797","https://openalex.org/W6600756316","https://openalex.org/W6601804787","https://openalex.org/W6604190760","https://openalex.org/W6607643177","https://openalex.org/W6778883912","https://openalex.org/W6810081322"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2021787609","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
