{"id":"https://openalex.org/W4413147672","doi":"https://doi.org/10.1109/cvpr52734.2025.01810","title":"Empowering Large Language Models with 3D Situation Awareness","display_name":"Empowering Large Language Models with 3D Situation Awareness","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147672","doi":"https://doi.org/10.1109/cvpr52734.2025.01810"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-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/A5114832227","display_name":"Zhihao Yuan","orcid":"https://orcid.org/0000-0003-3100-1252"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihao Yuan","raw_affiliation_strings":["FNii-Shenzhen, CUHKSZ"],"affiliations":[{"raw_affiliation_string":"FNii-Shenzhen, CUHKSZ","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104333211","display_name":"Yibo Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Peng","raw_affiliation_strings":["FNii-Shenzhen, CUHKSZ"],"affiliations":[{"raw_affiliation_string":"FNii-Shenzhen, CUHKSZ","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036242436","display_name":"Jinke Ren","orcid":"https://orcid.org/0000-0002-7409-6127"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinke Ren","raw_affiliation_strings":["FNii-Shenzhen, CUHKSZ"],"affiliations":[{"raw_affiliation_string":"FNii-Shenzhen, CUHKSZ","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054990714","display_name":"Yinghong Liao","orcid":"https://orcid.org/0000-0001-9128-1167"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghong Liao","raw_affiliation_strings":["FNii-Shenzhen, CUHKSZ"],"affiliations":[{"raw_affiliation_string":"FNii-Shenzhen, CUHKSZ","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101198400","display_name":"Yatong Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yatong Han","raw_affiliation_strings":["FNii-Shenzhen, CUHKSZ"],"affiliations":[{"raw_affiliation_string":"FNii-Shenzhen, CUHKSZ","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101026168","display_name":"Chun-Mei Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chun-Mei Feng","raw_affiliation_strings":["IHPC, A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"IHPC, A*STAR,Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113288135","display_name":"Hengshuang Zhao","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":false,"raw_author_name":"Hengshuang Zhao","raw_affiliation_strings":["HKU"],"affiliations":[{"raw_affiliation_string":"HKU","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101691639","display_name":"Guanbin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanbin Li","raw_affiliation_strings":["SYSU"],"affiliations":[{"raw_affiliation_string":"SYSU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009164482","display_name":"Shuguang Cui","orcid":"https://orcid.org/0000-0003-2608-775X"},"institutions":[{"id":"https://openalex.org/I4210105385","display_name":"Shanghai Stock Exchange","ror":"https://ror.org/01ecwsw76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210105385"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuguang Cui","raw_affiliation_strings":["SSE, CUHKSZ"],"affiliations":[{"raw_affiliation_string":"SSE, CUHKSZ","institution_ids":["https://openalex.org/I4210105385","https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107914677","display_name":"Zhen Li","orcid":"https://orcid.org/0000-0002-5685-3163"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I4210105385","display_name":"Shanghai Stock Exchange","ror":"https://ror.org/01ecwsw76","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210105385"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Li","raw_affiliation_strings":["SSE, CUHKSZ"],"affiliations":[{"raw_affiliation_string":"SSE, CUHKSZ","institution_ids":["https://openalex.org/I4210105385","https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5114832227"],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":2.8599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92357242,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"19435","last_page":"19445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9790999889373779,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9790999889373779,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9646000266075134,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9409999847412109,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6962173581123352},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40055859088897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6962173581123352},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40055859088897705}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311778","display_name":"China Association for Science and Technology","ror":"https://ror.org/035vmht26"},{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Driven":[0],"by":[1,85],"the":[2,11,36,60,87,115,120,146],"great":[3],"success":[4],"of":[5,38,119,150],"Large":[6],"Language":[7],"Models":[8,96],"(LLMs)":[9],"in":[10,17,42,48,130],"2D":[12,33],"image":[13],"domain,":[14],"their":[15],"application":[16],"3D":[18,31,43,131,147],"scene":[19],"understanding":[20],"has":[21],"emerged":[22],"as":[23],"a":[24,67,76,82,108],"new":[25],"trend.":[26],"A":[27],"key":[28],"difference":[29],"between":[30],"and":[32,63,93,102,117,157],"is":[34],"that":[35,141],"situation":[37,109,128],"an":[39],"egocentric":[40,61],"observer":[41],"scenes":[44],"can":[45],"change,":[46],"resulting":[47],"different":[49],"descriptions":[50,129],"(e.g.,":[51],"\"left\"":[52],"or":[53],"\"right\").":[54],"However,":[55],"current":[56],"LLM-based":[57],"methods":[58],"overlook":[59],"perspective":[62],"use":[64],"datasets":[65,156],"from":[66],"global":[68],"viewpoint.":[69],"To":[70],"address":[71],"this":[72],"issue,":[73],"we":[74,106],"propose":[75],"novel":[77],"approach":[78,136],"to":[79,98,112,126],"automatically":[80],"generate":[81],"situation-aware":[83],"dataset":[84],"leveraging":[86],"scanning":[88],"trajectory":[89],"during":[90],"data":[91],"collection":[92],"utilizing":[94],"Vision-Language":[95],"(VLMs)":[97],"produce":[99],"high-quality":[100],"captions":[101],"question-answer":[103],"pairs.":[104],"Furthermore,":[105],"introduce":[107],"grounding":[110],"module":[111],"explicitly":[113],"predict":[114],"position":[116],"orientation":[118],"observer\u2019s":[121],"viewpoint,":[122],"thereby":[123],"enabling":[124],"LLMs":[125,151],"ground":[127],"scenes.":[132],"We":[133],"evaluate":[134],"our":[135,142],"on":[137],"several":[138],"benchmarks,":[139],"demonstrating":[140],"method":[143],"effectively":[144],"enhances":[145],"situational":[148],"awareness":[149],"while":[152],"significantly":[153],"expanding":[154],"existing":[155],"reducing":[158],"manual":[159],"effort.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
