{"id":"https://openalex.org/W7147259774","doi":"https://doi.org/10.1109/tpami.2026.3679561","title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","display_name":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7147259774","doi":"https://doi.org/10.1109/tpami.2026.3679561","pmid":"https://pubmed.ncbi.nlm.nih.gov/41915509"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3679561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3679561","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.27507","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132553097","display_name":"Haifeng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Huang","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-2813-6574","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132722695","display_name":"Yilun Chen","orcid":null},"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":"Yilun Chen","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3372-8703","affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401173","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0003-4873-505X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehan Wang","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiangmiao Pang","orcid":"https://orcid.org/0000-0002-6711-9319"},"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":"Jiangmiao Pang","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6711-9319","affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132621570","display_name":"Zhou Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6121-0384","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38892005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"8","first_page":"9813","last_page":"9825"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9164999723434448,"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":0.9164999723434448,"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":0.013299999758601189,"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":0.013000000268220901,"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/object","display_name":"Object (grammar)","score":0.775600016117096},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.6589000225067139},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6054999828338623},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5909000039100647},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5702000260353088},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4830999970436096},{"id":"https://openalex.org/keywords/object-oriented-design","display_name":"Object-oriented design","score":0.47200000286102295},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4352000057697296},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4104999899864197}],"concepts":[{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.775600016117096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706000208854675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7010999917984009},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.6589000225067139},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5909000039100647},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5702000260353088},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4999000132083893},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C53073257","wikidata":"https://www.wikidata.org/wiki/Q7075021","display_name":"Object-oriented design","level":3,"score":0.47200000286102295},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4104999899864197},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.35760000348091125},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.34130001068115234},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3398999869823456},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2026.3679561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3679561","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41915509","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41915509","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2603.27507","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.27507","pdf_url":"https://arxiv.org/pdf/2603.27507","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.27507","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.27507","pdf_url":"https://arxiv.org/pdf/2603.27507","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1101031052","display_name":null,"funder_award_id":"U24A20326","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1339071713","display_name":null,"funder_award_id":"62572423","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,119,176],"multi-modal":[3],"large":[4],"language":[5],"models":[6],"(MLLMs)":[7],"have":[8],"shown":[9],"strong":[10],"potential":[11],"for":[12,149],"3D":[13,36,49,74,90,108,162,187],"scene":[14,75,177],"understanding.":[15],"However,":[16],"existing":[17],"methods":[18],"struggle":[19],"with":[20,34,62,80],"fine-grained":[21],"object":[22,53,77,103,179],"grounding":[23],"and":[24,32,69,97,110,140,169,181],"contextual":[25,63],"reasoning,":[26,130],"limiting":[27],"their":[28],"ability":[29],"to":[30,85,134,197],"interpret":[31],"interact":[33],"complex":[35],"environments.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,193],"present":[42],"Chat-Scene++,":[43],"an":[44],"MLLM":[45],"framework":[46],"that":[47],"represents":[48],"scenes":[50,57],"as":[51,58],"context-rich":[52,102],"sequences.":[54],"By":[55],"structuring":[56],"sequences":[59],"of":[60],"objects":[61,136],"semantics,":[64,99],"Chat-Scene++":[65,100,155],"enables":[66],"object-centric":[67,123],"representation":[68],"interaction.":[70],"It":[71],"decomposes":[72],"a":[73],"into":[76],"representations":[78],"paired":[79],"identifier":[81],"tokens,":[82],"allowing":[83],"LLMs":[84],"follow":[86],"instructions":[87],"across":[88],"diverse":[89],"vision-language":[91,163],"tasks.":[92],"To":[93],"capture":[94],"inter-object":[95],"relationships":[96],"global":[98],"extracts":[101],"features":[104,118],"using":[105,200],"large-scale":[106],"pre-trained":[107],"scene-level":[109],"2D":[111,202],"image-level":[112],"encoders,":[113],"unlike":[114],"the":[115,132,147],"isolated":[116],"per-object":[117],"Chat-Scene.":[120],"Its":[121],"flexible":[122],"design":[124],"also":[125],"supports":[126],"grounded":[127],"chain-of-thought":[128],"(G-CoT)":[129],"enabling":[131],"model":[133],"distinguish":[135],"at":[137],"both":[138],"category":[139],"spatial":[141,182],"levels":[142],"during":[143],"multi-step":[144],"inference.":[145],"Without":[146],"need":[148],"additional":[150],"task-specific":[151],"heads":[152],"or":[153],"fine-tuning,":[154],"achieves":[156],"state-of-the-art":[157],"performance":[158],"on":[159],"five":[160],"major":[161],"benchmarks:":[164],"ScanRefer,":[165],"Multi3DRefer,":[166],"Scan2Cap,":[167],"ScanQA,":[168],"SQA3D.":[170],"These":[171],"results":[172],"highlight":[173],"its":[174,195],"effectiveness":[175],"comprehension,":[178],"grounding,":[180],"reasoning.":[183],"Additionally,":[184],"without":[185],"reconstructing":[186],"worlds":[188],"through":[189],"computationally":[190],"expensive":[191],"processes,":[192],"demonstrate":[194],"applicability":[196],"real-world":[198],"scenarios":[199],"only":[201],"inputs.":[203]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-04-02T00:00:00"}