{"id":"https://openalex.org/W4402716166","doi":"https://doi.org/10.1109/cvpr52733.2024.01227","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","display_name":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402716166","doi":"https://doi.org/10.1109/cvpr52733.2024.01227"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01227","doi":"https://doi.org/10.1109/cvpr52733.2024.01227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01227","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"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/2312.00784","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081591501","display_name":"Mu Cai","orcid":"https://orcid.org/0009-0008-7967-9752","observed_orcids":["https://orcid.org/0009-0008-7967-9752"]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mu Cai","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448802","display_name":"Haotian Liu","orcid":"https://orcid.org/0000-0003-2872-4740","observed_orcids":["https://orcid.org/0000-0003-2872-4740","https://orcid.org/0009-0008-0080-7919"]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haotian Liu","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021827101","display_name":"Siva Karthik Mustikovela","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siva Karthik Mustikovela","raw_affiliation_strings":["Cruise LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cruise LLC","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067267836","display_name":"Gregory P. Meyer","orcid":"https://orcid.org/0000-0001-9444-5577","observed_orcids":["https://orcid.org/0000-0001-9444-5577"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gregory P. Meyer","raw_affiliation_strings":["Cruise LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cruise LLC","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079961895","display_name":"Yuning Chai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuning Chai","raw_affiliation_strings":["Cruise LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cruise LLC","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077824676","display_name":"Dennis Park","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dennis Park","raw_affiliation_strings":["Cruise LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cruise LLC","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112702739","display_name":"Yong Jae Lee","orcid":"https://orcid.org/0000-0001-9863-1270","observed_orcids":["https://orcid.org/0000-0001-9863-1270","https://orcid.org/0009-0003-0838-5670"]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Jae Lee","raw_affiliation_strings":["University of Wisconsin-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.0995,"has_fulltext":true,"cited_by_count":126,"citation_normalized_percentile":{"value":0.99381941,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"12914","last_page":"12923"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-prompting","display_name":"visual prompting","score":0.5419999957084656},{"id":"https://openalex.org/keywords/large-vision-language-models","display_name":"large vision-language models","score":0.7350000143051147},{"id":"https://openalex.org/keywords/bounding-box-prompts","display_name":"bounding box prompts","score":0.4699999988079071},{"id":"https://openalex.org/keywords/visual-commonsense-reasoning","display_name":"visual commonsense reasoning","score":0.8920000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638783812522888},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5325464606285095},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4167737066745758},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4153191149234772},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39251670241355896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36102062463760376}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr52733.2024.01227","doi":"https://doi.org/10.1109/cvpr52733.2024.01227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01227","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2312.00784","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.00784","pdf_url":"https://arxiv.org/pdf/2312.00784","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.2312.00784","doi":"https://doi.org/10.48550/arxiv.2312.00784","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.00784","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:2312.00784","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.00784","pdf_url":"https://arxiv.org/pdf/2312.00784","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":[{"id":"https://openalex.org/G1491865986","display_name":"CAREER: Weakly-Supervised Visual Scene Understanding: Combining Images and Videos, and Going Beyond Semantic Tags","funder_award_id":"2150012","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402716166.pdf","grobid_xml":"https://content.openalex.org/works/W4402716166.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1956340063","https://openalex.org/W2034966370","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2903073381","https://openalex.org/W2962749469","https://openalex.org/W2969876226","https://openalex.org/W2970608575","https://openalex.org/W2990138404","https://openalex.org/W2998356391","https://openalex.org/W3034727271","https://openalex.org/W3102995547","https://openalex.org/W3109959312","https://openalex.org/W3135367836","https://openalex.org/W3173909648","https://openalex.org/W4236965008","https://openalex.org/W4312960937","https://openalex.org/W4322718191","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4376312115","https://openalex.org/W4382490555","https://openalex.org/W4385644400","https://openalex.org/W4385645323","https://openalex.org/W4386185600","https://openalex.org/W4387294588","https://openalex.org/W4387596621","https://openalex.org/W4390873481","https://openalex.org/W4401024018","https://openalex.org/W4402727018","https://openalex.org/W4402727764","https://openalex.org/W4403081466","https://openalex.org/W7133193691"],"related_works":["https://openalex.org/W4416322369","https://openalex.org/W7196937269","https://openalex.org/W4393721071","https://openalex.org/W7223136788","https://openalex.org/W4403785789","https://openalex.org/W4415799075","https://openalex.org/W4416245624","https://openalex.org/W4387800098","https://openalex.org/W4403020990","https://openalex.org/W7131431487"],"abstract_inverted_index":{"While":[0],"existing":[1],"large":[2],"vision-language":[3],"multimodal":[4,47],"models":[5,124],"focus":[6],"on":[7,101],"whole":[8],"image":[9],"understanding,":[10],"there":[11],"is":[12],"a":[13,33,45,72,116],"prominent":[14],"gap":[15],"in":[16,125,135],"achieving":[17],"region-specific":[18],"comprehension.":[19],"Current":[20],"approaches":[21],"that":[22],"use":[23],"textual":[24],"coordinates":[25],"or":[26,76],"spatial":[27],"encodings":[28],"often":[29],"fail":[30],"to":[31,59,119],"provide":[32],"user-friendly":[34],"interface":[35],"for":[36,93],"visual":[37,54,84,127],"prompting.":[38],"To":[39],"address":[40],"this":[41,136],"challenge,":[42],"we":[43,113],"introduce":[44],"novel":[46],"model":[48,67,141],"capable":[49],"of":[50,123],"decoding":[51],"arbitrary":[52],"(free-form)":[53],"prompts.":[55],"This":[56],"allows":[57],"users":[58],"intuitively":[60],"mark":[61],"images":[62],"and":[63,107,140],"interact":[64],"with":[65],"the":[66,87,91,121],"using":[68],"natural":[69],"cues":[70],"like":[71,104],"\u201cred":[73],"bounding":[74],"box\u201d":[75],"\u201cpointed":[77],"arrow\u201d.":[78],"Our":[79],"simple":[80],"design":[81],"directly":[82],"overlays":[83],"markers":[85],"onto":[86],"RGB":[88],"image,":[89],"eliminating":[90],"need":[92],"complex":[94],"region":[95],"encodings,":[96],"yet":[97],"achieves":[98],"state-of-the-art":[99],"performance":[100],"region-understanding":[102],"tasks":[103],"Visual7W,":[105],"PointQA,":[106],"Visual":[108],"Commonsense":[109],"Reasoning":[110],"benchmark.":[111],"Furthermore,":[112],"present":[114],"ViP-Bench,":[115],"comprehensive":[117],"benchmark":[118],"assess":[120],"capability":[122],"understanding":[126],"prompts":[128],"across":[129],"multiple":[130],"dimensions,":[131],"enabling":[132],"future":[133],"research":[134],"domain.":[137],"Code,":[138],"data,":[139],"are":[142],"publicly":[143],"available.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":46},{"year":2025,"cited_by_count":51},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-09-22T00:00:00"}