{"id":"https://openalex.org/W4415709160","doi":"https://doi.org/10.1109/icme59968.2025.11208909","title":"Injecting Cross-modal Fine-Grained Perception into LLMs for 3D Object-of-Interest Understanding","display_name":"Injecting Cross-modal Fine-Grained Perception into LLMs for 3D Object-of-Interest Understanding","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709160","doi":"https://doi.org/10.1109/icme59968.2025.11208909"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11208909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101740305","display_name":"Qianqian Sun","orcid":"https://orcid.org/0000-0001-6362-904X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianqian Sun","raw_affiliation_strings":["Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100931299","display_name":"Lu Shi","orcid":"https://orcid.org/0000-0003-3203-630X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Shi","raw_affiliation_strings":["Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031690451","display_name":"Linna Zhang","orcid":"https://orcid.org/0000-0003-1751-8407"},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linna Zhang","raw_affiliation_strings":["Guizhou University,School of Mechanical Engineering,Guiyang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guizhou University,School of Mechanical Engineering,Guiyang,China","institution_ids":["https://openalex.org/I178232147"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054342134","display_name":"Gaoyun An","orcid":"https://orcid.org/0000-0002-2843-843X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoyun An","raw_affiliation_strings":["Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033896100","display_name":"Yi Jin","orcid":"https://orcid.org/0000-0001-8408-3816"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Jin","raw_affiliation_strings":["Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010019122","display_name":"Yidong Li","orcid":"https://orcid.org/0000-0003-2965-6196"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidong Li","raw_affiliation_strings":["Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082462498","display_name":"Yigang Cen","orcid":"https://orcid.org/0000-0001-6255-9422"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yigang Cen","raw_affiliation_strings":["Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.836899995803833,"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":0.836899995803833,"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":0.03009999915957451,"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":0.02930000051856041,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/perception","display_name":"Perception","score":0.7318999767303467},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7286999821662903},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6682000160217285},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5855000019073486}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7318999767303467},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7286999821662903},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6682000160217285},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.512499988079071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5041000247001648},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4749000072479248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35249999165534973},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3504999876022339},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29739999771118164},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2955000102519989},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11208909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W2460657278","https://openalex.org/W2594519801","https://openalex.org/W2970641574","https://openalex.org/W3107521863","https://openalex.org/W3156636935","https://openalex.org/W4214624153","https://openalex.org/W4226376247","https://openalex.org/W4285606658","https://openalex.org/W4312253406","https://openalex.org/W4313262066","https://openalex.org/W4386076628","https://openalex.org/W4394773594","https://openalex.org/W4399310957","https://openalex.org/W4402716423","https://openalex.org/W4409129939","https://openalex.org/W4411113252"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,12,40,42],"3D":[3,17,31,67,81,91],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"have":[8,22],"revealed":[9],"significant":[10],"potential":[11],"enhancing":[13,61],"the":[14,34,47,55,62,73,79,86],"understanding":[15,43,68],"of":[16,30,36,64,72],"scenes.":[18],"However,":[19],"previous":[20],"methods":[21,113],"struggled":[23],"with":[24,90],"extracting":[25],"and":[26,78,118],"utilizing":[27],"fine-grained":[28,74],"information":[29],"objects":[32,92],"for":[33,60,66],"coarsness":[35],"point":[37],"clouds,":[38],"resulting":[39],"limitations":[41],"object-of-interested":[44],"(OoI)":[45],"within":[46],"scene.":[48],"To":[49],"address":[50],"this":[51],"issue,":[52],"we":[53],"introduce":[54],"object-centric":[56,80],"2D-3D":[57],"interaction":[58],"module":[59],"ability":[63],"LLMs":[65],"tasks,":[69],"which":[70],"consists":[71],"2D":[75,87],"representation":[76,83,88],"perception":[77],"scene":[82],"perception.":[84],"Specifically,":[85],"associated":[89],"is":[93],"captured":[94],"based":[95],"on":[96,114],"cross-modal":[97],"semantic":[98],"consistency":[99],"without":[100],"any":[101],"spatial":[102],"projector.":[103],"Experimental":[104],"results":[105],"show":[106],"that":[107],"our":[108],"model":[109],"significantly":[110],"outperforms":[111],"existing":[112],"benchmarks":[115],"including":[116],"ScanRefer":[117],"ScanQA.":[119]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}