{"id":"https://openalex.org/W7131898060","doi":"https://doi.org/10.1109/tmm.2026.3668502","title":"3D-SceneQ: Empowering 3D LLM With Query-Guided Adaptive Pruning and Multi-Modal Feature Enhancement","display_name":"3D-SceneQ: Empowering 3D LLM With Query-Guided Adaptive Pruning and Multi-Modal Feature Enhancement","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131898060","doi":"https://doi.org/10.1109/tmm.2026.3668502"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3668502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668502","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5054488451","display_name":"Yongqi Shan","orcid":null},"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":"Yongqi Shan","raw_affiliation_strings":["School of Artificial Intelligence, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127270026","display_name":"Lu Zhang","orcid":null},"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":"Lu Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-4648-4437","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045820924","display_name":"Jiazuo Yu","orcid":null},"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":"Jiazuo Yu","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0007-6758-7407","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048521072","display_name":"Yunzhi Zhuge","orcid":"https://orcid.org/0000-0002-4288-4516"},"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":"Yunzhi Zhuge","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-4288-4516","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127353622","display_name":"Huchuan Lu","orcid":null},"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":"Huchuan Lu","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-6668-9758","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15920939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"5972","last_page":"5983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2540000081062317,"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":0.2540000081062317,"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":0.17749999463558197,"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"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.08060000091791153,"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/security-token","display_name":"Security token","score":0.5805000066757202},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5758000016212463},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5547000169754028},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5067999958992004},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.44429999589920044},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44190001487731934},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4397999942302704},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.37229999899864197},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.3698999881744385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8863999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.61080002784729},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5805000066757202},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5758000016212463},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5547000169754028},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5067999958992004},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.400299996137619},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.33399999141693115},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3668502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668502","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1358076444","display_name":null,"funder_award_id":"DUT24YG119","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3080167161","display_name":null,"funder_award_id":"62206039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4319081443","display_name":null,"funder_award_id":"DUT24RC(3)025","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4585823974","display_name":null,"funder_award_id":"62441231","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6387696347","display_name":null,"funder_award_id":"62406053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2594519801","https://openalex.org/W2896457183","https://openalex.org/W2911486422","https://openalex.org/W2963250244","https://openalex.org/W2964339842","https://openalex.org/W2966683369","https://openalex.org/W2970641574","https://openalex.org/W2981422075","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3159746229","https://openalex.org/W3170262190","https://openalex.org/W3182910454","https://openalex.org/W3209992943","https://openalex.org/W4226376247","https://openalex.org/W4310463627","https://openalex.org/W4312270234","https://openalex.org/W4312818263","https://openalex.org/W4312912313","https://openalex.org/W4386065742","https://openalex.org/W4386075660","https://openalex.org/W4386076097","https://openalex.org/W4386076628","https://openalex.org/W4390872495","https://openalex.org/W4390872570","https://openalex.org/W4392669753","https://openalex.org/W4392693642","https://openalex.org/W4401991200","https://openalex.org/W4402703032","https://openalex.org/W4402716272","https://openalex.org/W4402727922","https://openalex.org/W4402961666","https://openalex.org/W4403778769","https://openalex.org/W4405572026","https://openalex.org/W4406857575","https://openalex.org/W4407128859","https://openalex.org/W4409129939","https://openalex.org/W4409991262","https://openalex.org/W4413146469","https://openalex.org/W4413156557","https://openalex.org/W7133184052","https://openalex.org/W7133193597","https://openalex.org/W7133196460","https://openalex.org/W7133205816","https://openalex.org/W7133205985","https://openalex.org/W7133246057","https://openalex.org/W7133250029"],"related_works":[],"abstract_inverted_index":{"Current":[0],"3D":[1,10,91,165,199],"scene":[2,31,104],"understanding":[3,32],"pipelines":[4],"typically":[5],"concatenate":[6],"vast":[7],"numbers":[8],"of":[9,40,128],"object":[11,42],"tokens":[12,15],"with":[13,98],"text":[14],"and":[16,50,53,79,107,188],"feed":[17],"the":[18,64,125],"resulting":[19],"sequence":[20],"to":[21,136,167],"a":[22,90,112,132,149],"Large":[23],"Language":[24],"Model":[25],"(LLM).":[26],"However,":[27],"existing":[28],"3D-LLMs":[29],"for":[30],"encounter":[33],"two":[34],"major":[35],"limitations:":[36],"(i)":[37],"excessive":[38],"inclusion":[39],"task-irrelevant":[41],"data,":[43,60],"introducing":[44],"noise":[45],"that":[46,93,118,174],"reduces":[47],"reasoning":[48,201],"accuracy":[49],"increases":[51],"hallucinations;":[52],"(ii)":[54],"reliance":[55],"solely":[56],"on":[57,124,186,191],"point":[58],"cloud":[59],"which":[61,156],"inherently":[62],"lacks":[63],"rich":[65],"semantic":[66,100,170],"information":[67,139],"available":[68],"in":[69,197],"complementary":[70],"2D":[71,158],"modalities,":[72],"such":[73],"as":[74],"color,":[75],"material":[76],"properties,":[77],"texture,":[78],"high-level":[80],"contextual":[81],"relationships.":[82],"To":[83],"address":[84],"these":[85],"challenges,":[86],"we":[87,110,147],"introduce":[88,148],"3D-SceneQ,":[89],"LLM":[92],"unifies":[94],"adaptive":[95],"token":[96],"pruning":[97],"multimodal":[99],"enrichment,":[101],"markedly":[102],"advancing":[103],"understanding,":[105],"reasoning,":[106],"grounding.":[108],"Specifically,":[109],"propose":[111],"Query-Guided":[113],"Adaptive":[114],"Pruning":[115],"(QGAP)":[116],"module":[117],"adaptively":[119],"selects":[120],"task-relevant":[121],"objects":[122],"based":[123],"intended":[126],"meaning":[127],"user":[129],"instructions,":[130],"leveraging":[131],"learnable":[133],"latent":[134],"query":[135],"retain":[137],"critical":[138],"while":[140],"effectively":[141],"suppressing":[142],"irrelevant":[143],"noise.":[144],"In":[145],"addition,":[146],"Multi-modal":[150],"Object-level":[151],"Feature":[152],"Enhancement":[153],"(MOFE)":[154],"module,":[155],"integrates":[157],"feature":[159],"embeddings":[160],"from":[161],"pre-trained":[162],"models":[163],"into":[164],"representation":[166],"enrich":[168],"object-level":[169],"information.":[171],"Evaluations":[172],"show":[173],"3D-SceneQ":[175],"outperforms":[176],"current":[177],"state-of-the-art":[178],"methods":[179],"across":[180],"multiple":[181],"benchmarks":[182],"(e.g.,":[183],"+5.7":[184],"CIDEr":[185],"Scan2Cap":[187],"+17.0":[189],"EM@1":[190],"SQA3D),":[192],"demonstrating":[193],"its":[194],"remarkable":[195],"capabilities":[196],"various":[198],"language":[200],"tasks.":[202]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-02-28T00:00:00"}