{"id":"https://openalex.org/W4403081598","doi":"https://doi.org/10.1007/978-3-031-72658-3_24","title":"Groma: Localized Visual Tokenization for\u00a0Grounding Multimodal Large Language Models","display_name":"Groma: Localized Visual Tokenization for\u00a0Grounding Multimodal Large Language Models","publication_year":2024,"publication_date":"2024-10-02","ids":{"openalex":"https://openalex.org/W4403081598","doi":"https://doi.org/10.1007/978-3-031-72658-3_24"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-72658-3_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-72658-3_24","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/A5008623498","display_name":"Chuofan Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Chuofan Ma","raw_affiliation_strings":["The University of Hong Kong, Pokfulam, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003190764","display_name":"Yi Jiang","orcid":"https://orcid.org/0000-0002-2133-8719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Jiang","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032789289","display_name":"Jiannan Wu","orcid":"https://orcid.org/0009-0001-6367-6994"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiannan Wu","raw_affiliation_strings":["The University of Hong Kong, Pokfulam, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039592275","display_name":"Zehuan Yuan","orcid":"https://orcid.org/0000-0002-0349-9367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehuan Yuan","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102498323","display_name":"Xiaojuan Qi","orcid":"https://orcid.org/0000-0002-4285-1626"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaojuan Qi","raw_affiliation_strings":["The University of Hong Kong, Pokfulam, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008623498"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":8.7737,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.98645476,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"417","last_page":"435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9926000237464905,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9857000112533569,"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/computer-science","display_name":"Computer science","score":0.8641465902328491},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.7163517475128174},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.6441824436187744},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46484747529029846},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4457799792289734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4432781934738159},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3645992577075958},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11454439163208008},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.051491111516952515}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8641465902328491},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.7163517475128174},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6441824436187744},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46484747529029846},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4457799792289734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4432781934738159},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3645992577075958},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11454439163208008},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.051491111516952515}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-72658-3_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-72658-3_24","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":46,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2948672349","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2983943451","https://openalex.org/W3135367836","https://openalex.org/W3159619744","https://openalex.org/W4221143046","https://openalex.org/W4225323055","https://openalex.org/W4281633595","https://openalex.org/W4288083516","https://openalex.org/W4312424618","https://openalex.org/W4312446817","https://openalex.org/W4312815172","https://openalex.org/W4376312115","https://openalex.org/W4377164404","https://openalex.org/W4386065815","https://openalex.org/W4386185600","https://openalex.org/W4387687151","https://openalex.org/W4389519620","https://openalex.org/W4390871915","https://openalex.org/W4402713111","https://openalex.org/W4402716166","https://openalex.org/W4402727018","https://openalex.org/W4402727558","https://openalex.org/W4402727764","https://openalex.org/W4402753807","https://openalex.org/W4402754134","https://openalex.org/W4402952458","https://openalex.org/W4403906565","https://openalex.org/W4404575065","https://openalex.org/W4404612908","https://openalex.org/W6600008909","https://openalex.org/W6600042225","https://openalex.org/W6600137863","https://openalex.org/W6600140940","https://openalex.org/W6600234944","https://openalex.org/W6600574797","https://openalex.org/W6600648412","https://openalex.org/W6600756316","https://openalex.org/W6851607685","https://openalex.org/W6912494966"],"related_works":["https://openalex.org/W4386014872","https://openalex.org/W1847536016","https://openalex.org/W4300598845","https://openalex.org/W2601638452","https://openalex.org/W2285263069","https://openalex.org/W4319309671","https://openalex.org/W4376107815","https://openalex.org/W4319309603","https://openalex.org/W1599985958","https://openalex.org/W1748623649"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}