{"id":"https://openalex.org/W4401991200","doi":"https://doi.org/10.1109/icmew63481.2024.10645462","title":"3DMIT: 3D Multi-Modal Instruction Tuning for Scene Understanding","display_name":"3DMIT: 3D Multi-Modal Instruction Tuning for Scene Understanding","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4401991200","doi":"https://doi.org/10.1109/icmew63481.2024.10645462"},"language":"en","primary_location":{"id":"doi:10.1109/icmew63481.2024.10645462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew63481.2024.10645462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5074707604","display_name":"Zeju Li","orcid":"https://orcid.org/0000-0002-4608-2959"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zeju Li","raw_affiliation_strings":["Beijing Digital Native Digital City Research Center"],"affiliations":[{"raw_affiliation_string":"Beijing Digital Native Digital City Research Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460272","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0003-3009-598X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Beijing Digital Native Digital City Research Center"],"affiliations":[{"raw_affiliation_string":"Beijing Digital Native Digital City Research Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381793","display_name":"Xiaoyan Wang","orcid":"https://orcid.org/0000-0002-7651-7730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyan Wang","raw_affiliation_strings":["Beijing Digital Native Digital City Research Center"],"affiliations":[{"raw_affiliation_string":"Beijing Digital Native Digital City Research Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041338432","display_name":"Ruilong Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruilong Ren","raw_affiliation_strings":["Beijing Digital Native Digital City Research Center"],"affiliations":[{"raw_affiliation_string":"Beijing Digital Native Digital City Research Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103166791","display_name":"Yifan Xu","orcid":"https://orcid.org/0000-0003-2467-888X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Xu","raw_affiliation_strings":["Beijing Digital Native Digital City Research Center"],"affiliations":[{"raw_affiliation_string":"Beijing Digital Native Digital City Research Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067770870","display_name":"Ruifei Ma","orcid":"https://orcid.org/0000-0002-2546-3867"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruifei Ma","raw_affiliation_strings":["Beijing Digital Native Digital City Research Center"],"affiliations":[{"raw_affiliation_string":"Beijing Digital Native Digital City Research Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062045482","display_name":"Xiangde Liu","orcid":"https://orcid.org/0000-0003-3087-0472"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangde Liu","raw_affiliation_strings":["Beijing Digital Native Digital City Research Center"],"affiliations":[{"raw_affiliation_string":"Beijing Digital Native Digital City Research Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064602921","display_name":"Wei Rong","orcid":"https://orcid.org/0000-0002-8550-6574"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Wei","raw_affiliation_strings":["Beijing Digital Native Digital City Research Center"],"affiliations":[{"raw_affiliation_string":"Beijing Digital Native Digital City Research Center","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5074707604"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.9035,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.99064381,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.968500018119812,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9664999842643738,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.7563976049423218},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6891176700592041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3718070983886719},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05755302309989929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7563976049423218},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6891176700592041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3718070983886719},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05755302309989929},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew63481.2024.10645462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew63481.2024.10645462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2594519801","https://openalex.org/W2966683369","https://openalex.org/W2979912832","https://openalex.org/W3107521863","https://openalex.org/W3168867926","https://openalex.org/W4226376247","https://openalex.org/W4322718191","https://openalex.org/W4366330503","https://openalex.org/W4380558379","https://openalex.org/W4385262477","https://openalex.org/W4386044453","https://openalex.org/W4386555501","https://openalex.org/W4387561477","https://openalex.org/W4393149778","https://openalex.org/W4401416853","https://openalex.org/W4402727761","https://openalex.org/W4402727764"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"The":[0],"remarkable":[1],"potential":[2],"of":[3,23,37,42,84,132,157],"multi-modal":[4],"large":[5],"language":[6,14,110],"models":[7],"(MLLMs)":[8],"in":[9,27,40,138],"comprehending":[10],"both":[11],"vision":[12],"and":[13,55,77,94,109,111,125,143],"information":[15,87,120],"has":[16],"been":[17],"widely":[18],"acknowledged.":[19],"However,":[20],"the":[21,35,82,103,113,117,122,130,139,158],"scarcity":[22],"3D":[24,43,66,74,85,107,118,140,159],"scenes-language":[25],"pairs":[26,63],"comparison":[28],"to":[29,73,153],"their":[30],"2D":[31],"counterparts,":[32],"coupled":[33],"with":[34,116],"inadequacy":[36],"existing":[38],"approaches":[39],"understanding":[41],"scenes":[44,108],"by":[45],"LLMs,":[46,89],"poses":[47],"a":[48,92,150],"significant":[49],"challenge.":[50],"In":[51],"response,":[52],"we":[53,90],"collect":[54],"construct":[56],"an":[57],"extensive":[58],"dataset":[59,69],"comprising":[60],"75K":[61],"instruction-response":[62],"tailored":[64],"for":[65],"scenes.":[67],"This":[68,100],"addresses":[70],"tasks":[71,137],"related":[72],"VQA,":[75],"grounding,":[76],"caption.":[78],"To":[79],"further":[80],"enhance":[81],"integration":[83],"spatial":[86],"into":[88],"introduce":[91],"novel":[93],"efficient":[95],"prompt":[96,115],"tuning":[97],"paradigm,":[98],"3DMIT.":[99],"paradigm":[101],"eliminates":[102],"alignment":[104],"stage":[105],"between":[106],"extends":[112],"instruction":[114],"modality":[119],"including":[121],"entire":[123],"scene":[124,141],"segmented":[126],"objects.":[127],"We":[128],"evaluate":[129],"effectiveness":[131],"our":[133,146],"method":[134],"across":[135],"diverse":[136],"domain":[142],"find":[144],"that":[145],"approach":[147],"serves":[148],"as":[149],"strategic":[151],"means":[152],"enrich":[154],"LLMs'":[155],"comprehension":[156],"world.":[160],"Our":[161],"code":[162],"is":[163],"available":[164],"at":[165],"https://github.com/staymylove/3DMIT.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":4}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}