{"id":"https://openalex.org/W4389911992","doi":"https://doi.org/10.48550/arxiv.2312.09738","title":"3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V","display_name":"3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4389911992","doi":"https://doi.org/10.48550/arxiv.2312.09738"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.09738","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.09738","pdf_url":"https://arxiv.org/pdf/2312.09738","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":"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/2312.09738","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109613883","display_name":"Dingning Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"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":"Liu, Dingning","raw_affiliation_strings":["Dalian University of Technology","Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045520525","display_name":"Xiaomeng Dong","orcid":"https://orcid.org/0000-0002-2802-8406","observed_orcids":["https://orcid.org/0000-0002-2802-8406"]},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong, Xiaomeng","raw_affiliation_strings":["Northeast Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102891082","display_name":"Renrui Zhang","orcid":"https://orcid.org/0000-0003-4503-5277","observed_orcids":["https://orcid.org/0000-0003-4503-5277","https://orcid.org/0009-0009-5414-7087"]},"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":"Zhang, Renrui","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence 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":null,"display_name":"Luo, Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo, Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039420666","display_name":"Peng Gao","orcid":"https://orcid.org/0000-0002-2110-7427","observed_orcids":["https://orcid.org/0000-0002-2110-7427"]},"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":"Gao, Peng","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043863561","display_name":"Xiaoshui Huang","orcid":"https://orcid.org/0000-0002-3579-538X","observed_orcids":["https://orcid.org/0000-0002-3579-538X"]},"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":"Huang, Xiaoshui","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040047825","display_name":"Yongshun Gong","orcid":"https://orcid.org/0000-0003-3948-4471","observed_orcids":["https://orcid.org/0000-0003-3948-4471"]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gong, Yongshun","raw_affiliation_strings":["Shandong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026090096","display_name":"Zhihui Wang","orcid":"https://orcid.org/0000-0001-8140-1882","observed_orcids":["https://orcid.org/0000-0001-8140-1882"]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zhihui","raw_affiliation_strings":["Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"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":0.44920000433921814,"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":0.44920000433921814,"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":0.271699994802475,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.09200000017881393,"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/visual-prompting","display_name":"visual prompting","score":0.8050000071525574},{"id":"https://openalex.org/keywords/gpt-4v","display_name":"GPT-4V","score":0.9789999723434448},{"id":"https://openalex.org/keywords/3d-spatial-reasoning","display_name":"3D spatial reasoning","score":0.902999997138977},{"id":"https://openalex.org/keywords/three-dimensional-coordinate-system","display_name":"three-dimensional coordinate system","score":0.9309999942779541},{"id":"https://openalex.org/keywords/3d-object-detection","display_name":"3D object detection","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7150951623916626},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6898947358131409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6324730515480042},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5473341345787048},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.49594101309776306},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4395182728767395},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4115184545516968},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41013506054878235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3632426857948303},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.18157660961151123},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13239923119544983},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.09981796145439148},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08255746960639954},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.09738","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.09738","pdf_url":"https://arxiv.org/pdf/2312.09738","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2312.09738","doi":"https://doi.org/10.48550/arxiv.2312.09738","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.09738","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:2312.09738","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.09738","pdf_url":"https://arxiv.org/pdf/2312.09738","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389911992.pdf","grobid_xml":"https://content.openalex.org/works/W4389911992.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W3031931231","https://openalex.org/W3036020516","https://openalex.org/W3095411714","https://openalex.org/W3098267758","https://openalex.org/W4206792893","https://openalex.org/W4281838252","https://openalex.org/W4311992366","https://openalex.org/W4312367717","https://openalex.org/W4318718936","https://openalex.org/W4319452690","https://openalex.org/W4322718191","https://openalex.org/W4323717348","https://openalex.org/W4360836968","https://openalex.org/W4361229539","https://openalex.org/W4366850747","https://openalex.org/W4372283850","https://openalex.org/W4385431115","https://openalex.org/W4385768219","https://openalex.org/W4386044453","https://openalex.org/W4386436509","https://openalex.org/W4386555501","https://openalex.org/W4387800098","https://openalex.org/W4390873481","https://openalex.org/W4391451889","https://openalex.org/W4393148310","https://openalex.org/W4393149778","https://openalex.org/W4402727002","https://openalex.org/W4402727761","https://openalex.org/W4403778769","https://openalex.org/W7133205985","https://openalex.org/W7133246057"],"related_works":["https://openalex.org/W6891880591","https://openalex.org/W4406033487","https://openalex.org/W4415797143","https://openalex.org/W7168244276","https://openalex.org/W4415800665","https://openalex.org/W7133351226","https://openalex.org/W7162770711","https://openalex.org/W7162795478","https://openalex.org/W7141467982","https://openalex.org/W4413157552"],"abstract_inverted_index":{"In":[0,58],"this":[1],"work,":[2],"we":[3,61,87],"present":[4],"a":[5,63,103,159],"new":[6],"visual":[7,43,83],"prompting":[8,44],"method":[9],"called":[10],"3DAxiesPrompts":[11],"(3DAP)":[12],"to":[13,55,68,90,125,130],"unleash":[14],"the":[15,34,81,92,97,120,146,152],"capabilities":[16],"of":[17,38,96,106,154],"GPT-4V":[18,29,89,156],"in":[19,32,48,162],"performing":[20],"3D":[21,50,64,69,99,126,131,135,163],"spatial":[22,51,93,164],"tasks.":[23],"Our":[24],"investigation":[25],"reveals":[26],"that":[27,114],"while":[28],"exhibits":[30],"proficiency":[31],"discerning":[33],"position":[35],"and":[36,134],"interrelations":[37],"2D":[39,124,129],"entities":[40],"through":[41],"current":[42],"techniques,":[45],"its":[46],"abilities":[47],"handling":[49],"tasks":[52,113],"have":[53],"yet":[54],"be":[56,116],"explored.":[57],"our":[59,142],"approach,":[60],"create":[62],"coordinate":[65],"system":[66],"tailored":[67],"imagery,":[70],"complete":[71],"with":[72,80,102],"annotated":[73],"scale":[74],"information.":[75],"By":[76],"presenting":[77],"images":[78],"infused":[79],"3DAP":[82,121],"prompt":[84],"as":[85],"inputs,":[86,157],"empower":[88],"ascertain":[91],"positioning":[94],"information":[95],"given":[98],"target":[100],"image":[101],"high":[104],"degree":[105],"precision.":[107],"Through":[108],"experiments,":[109],"We":[110,138],"identified":[111],"three":[112],"could":[115],"stably":[117],"completed":[118],"using":[119],"method,":[122],"namely,":[123],"Point":[127],"Reconstruction,":[128],"point":[132],"matching,":[133],"Object":[136],"Detection.":[137],"perform":[139],"experiments":[140,150],"on":[141],"proposed":[143],"dataset":[144],"3DAP-Data,":[145],"results":[147],"from":[148],"these":[149],"validate":[151],"efficacy":[153],"3DAP-enhanced":[155],"marking":[158],"significant":[160],"stride":[161],"task":[165],"execution.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2023-12-19T00:00:00"}