{"id":"https://openalex.org/W4401770219","doi":"https://doi.org/10.1007/s11263-024-02214-4","title":"Contextual Object Detection with Multimodal Large Language Models","display_name":"Contextual Object Detection with Multimodal Large Language Models","publication_year":2024,"publication_date":"2024-08-20","ids":{"openalex":"https://openalex.org/W4401770219","doi":"https://doi.org/10.1007/s11263-024-02214-4"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-024-02214-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-024-02214-4","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-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/A5005200501","display_name":"Yuhang Zang","orcid":"https://orcid.org/0000-0003-1110-5062"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuhang Zang","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115591090","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-9791-9763"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101898844","display_name":"Jun Han","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jun Han","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030812622","display_name":"Kaiyang Zhou","orcid":"https://orcid.org/0000-0002-8153-3903"},"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":"Kaiyang Zhou","raw_affiliation_strings":["Hong Kong Baptist University, Kowloon Tong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005626854","display_name":"Chen Change Loy","orcid":"https://orcid.org/0000-0001-5345-1591"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Chen Change Loy","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005626854"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":null,"fwci":17.013,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.9958137,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"133","issue":"2","first_page":"825","last_page":"843"},"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":0.9854000210762024,"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":0.9753999710083008,"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":0.837561845779419},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7184140682220459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6838256120681763},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6010524034500122},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5001211166381836},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49735501408576965},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48507848381996155},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.47985929250717163},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46391645073890686},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4449057877063751},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.44176262617111206},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.42559731006622314},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3371860682964325},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24618664383888245},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10727187991142273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.837561845779419},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7184140682220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6838256120681763},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6010524034500122},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5001211166381836},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49735501408576965},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48507848381996155},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.47985929250717163},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46391645073890686},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4449057877063751},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.44176262617111206},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.42559731006622314},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3371860682964325},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24618664383888245},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10727187991142273},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11263-024-02214-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-024-02214-4","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/181063","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/181063","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W2031489346","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2125215748","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2520951797","https://openalex.org/W2550553598","https://openalex.org/W2560730294","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2895403383","https://openalex.org/W2948672349","https://openalex.org/W2962766617","https://openalex.org/W2963150697","https://openalex.org/W2963936013","https://openalex.org/W2964284374","https://openalex.org/W2981852735","https://openalex.org/W2982770724","https://openalex.org/W2983943451","https://openalex.org/W3012573144","https://openalex.org/W3092462694","https://openalex.org/W3096609285","https://openalex.org/W3126337491","https://openalex.org/W3135367836","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3171547673","https://openalex.org/W3173859428","https://openalex.org/W3176659256","https://openalex.org/W3177174258","https://openalex.org/W3199245537","https://openalex.org/W3206072662","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4212774754","https://openalex.org/W4221146106","https://openalex.org/W4225323055","https://openalex.org/W4241200240","https://openalex.org/W4282919422","https://openalex.org/W4284961860","https://openalex.org/W4288083516","https://openalex.org/W4297899309","https://openalex.org/W4310557340","https://openalex.org/W4312424618","https://openalex.org/W4312563428","https://openalex.org/W4312605942","https://openalex.org/W4312747482","https://openalex.org/W4312956471","https://openalex.org/W4321612728","https://openalex.org/W4386075493","https://openalex.org/W4386076029","https://openalex.org/W4386076222","https://openalex.org/W4386076396","https://openalex.org/W4389519987","https://openalex.org/W4390871915","https://openalex.org/W4390874575","https://openalex.org/W4402727764","https://openalex.org/W4404612908","https://openalex.org/W6600234944","https://openalex.org/W6639102338","https://openalex.org/W6723035356","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6778883912","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W4327500857","https://openalex.org/W2965994363","https://openalex.org/W4311223090","https://openalex.org/W1689909837","https://openalex.org/W4205729548","https://openalex.org/W4298525700","https://openalex.org/W1895541646","https://openalex.org/W2953362004","https://openalex.org/W2952251705","https://openalex.org/W2889698616"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
