{"id":"https://openalex.org/W4403580243","doi":"https://doi.org/10.48550/arxiv.2410.13860","title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","display_name":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4403580243","doi":"https://doi.org/10.48550/arxiv.2410.13860"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.13860","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.13860","pdf_url":"https://arxiv.org/pdf/2410.13860","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.13860","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075229879","display_name":"Runsen Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Xu, Runsen","raw_affiliation_strings":["Shanghai AI Laboratory","The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012677359","display_name":"Zhiwei Huang","orcid":"https://orcid.org/0000-0002-6312-7434","observed_orcids":["https://orcid.org/0000-0002-6312-7434"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Zhiwei","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101840761","display_name":"Tai Wang","orcid":"https://orcid.org/0000-0002-5069-865X","observed_orcids":["https://orcid.org/0000-0002-5069-865X","https://orcid.org/0000-0001-6907-492X"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Tai","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101537280","display_name":"Yilun Chen","orcid":"https://orcid.org/0000-0001-9724-5079","observed_orcids":["https://orcid.org/0000-0001-9724-5079"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Yilun","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pang, Jiangmiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pang, Jiangmiao","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896","observed_orcids":["https://orcid.org/0000-0002-8865-7896"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Dahua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8525000214576721,"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":0.8525000214576721,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.11720000207424164,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.006500000134110451,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/3d-visual-grounding","display_name":"3D visual grounding","score":0.9520000219345093},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9919999837875366},{"id":"https://openalex.org/keywords/2d-images","display_name":"2D images","score":0.8069999814033508},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.4350000023841858},{"id":"https://openalex.org/keywords/3d-bounding-box-estimation","display_name":"3D bounding box estimation","score":0.9929999709129333},{"id":"https://openalex.org/keywords/scanrefer","display_name":"ScanRefer","score":0.7979999780654907}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7462494969367981},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.547200620174408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45309358835220337},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3788973093032837},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.37478557229042053},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.3478122353553772},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2551317512989044},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09425023198127747},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08034816384315491},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.13860","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.13860","pdf_url":"https://arxiv.org/pdf/2410.13860","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.13860","doi":"https://doi.org/10.48550/arxiv.2410.13860","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.13860","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.13860","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.13860","pdf_url":"https://arxiv.org/pdf/2410.13860","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403580243.pdf","grobid_xml":"https://content.openalex.org/works/W4403580243.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2786036844","https://openalex.org/W2896457183","https://openalex.org/W4322718191","https://openalex.org/W4327810158","https://openalex.org/W4398156429","https://openalex.org/W4402716047","https://openalex.org/W4402961691","https://openalex.org/W4403760933","https://openalex.org/W4404783136","https://openalex.org/W4405079066"],"related_works":["https://openalex.org/W4416048548","https://openalex.org/W7127647844","https://openalex.org/W4413144643","https://openalex.org/W7162417772","https://openalex.org/W7158765577","https://openalex.org/W7155658732","https://openalex.org/W4416260731","https://openalex.org/W7164030591","https://openalex.org/W4415536948","https://openalex.org/W7148238561"],"abstract_inverted_index":{"3D":[0,13,23,74,107,135],"visual":[1,75],"grounding":[2,76,89],"is":[3],"crucial":[4],"for":[5,72],"robots,":[6],"requiring":[7],"integration":[8],"of":[9],"natural":[10],"language":[11],"and":[12,90,98,113,127],"scene":[14],"understanding.":[15],"Traditional":[16],"methods":[17,33,47],"depending":[18],"on":[19,79,111,125,130,134],"supervised":[20],"learning":[21],"with":[22],"point":[24],"clouds":[25],"are":[26,141],"limited":[27],"by":[28],"scarce":[29],"datasets.":[30],"Recently":[31],"zero-shot":[32,73,120],"leveraging":[34],"LLMs":[35],"have":[36],"been":[37],"proposed":[38],"to":[39,55,93,104],"address":[40],"the":[41,95],"data":[42],"issue.":[43],"While":[44],"effective,":[45],"these":[46],"only":[48],"use":[49],"object-centric":[50],"information,":[51],"limiting":[52],"their":[53],"ability":[54],"handle":[56],"complex":[57],"queries.":[58],"In":[59],"this":[60],"work,":[61],"we":[62],"present":[63],"VLM-Grounder,":[64],"a":[65,88,100],"novel":[66],"framework":[67],"using":[68],"vision-language":[69],"models":[70],"(VLMs)":[71],"based":[77],"solely":[78],"2D":[80],"images.":[81],"VLM-Grounder":[82,117],"dynamically":[83],"stitches":[84],"image":[85],"sequences,":[86],"employs":[87],"feedback":[91],"scheme":[92],"find":[94],"target":[96],"object,":[97],"uses":[99],"multi-view":[101],"ensemble":[102],"projection":[103],"accurately":[105],"estimate":[106],"bounding":[108],"boxes.":[109],"Experiments":[110],"ScanRefer":[112,126],"Nr3D":[114],"datasets":[115],"show":[116],"outperforms":[118],"previous":[119],"methods,":[121],"achieving":[122],"51.6%":[123],"Acc@0.25":[124],"48.0%":[128],"Acc":[129],"Nr3D,":[131],"without":[132],"relying":[133],"geometry":[136],"or":[137],"object":[138],"priors.":[139],"Codes":[140],"available":[142],"at":[143],"https://github.com/OpenRobotLab/VLM-Grounder":[144],".":[145]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-10-21T00:00:00"}