{"id":"https://openalex.org/W7131900859","doi":"https://doi.org/10.1109/tmm.2026.3668488","title":"Rendered 2D Semantic and Generative Priors Guided 3D Multi-Object Grounding","display_name":"Rendered 2D Semantic and Generative Priors Guided 3D Multi-Object Grounding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131900859","doi":"https://doi.org/10.1109/tmm.2026.3668488"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3668488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668488","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/A5127195938","display_name":"Peng Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Guo","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-9848-2272","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127332243","display_name":"Hongyuan Zhu","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"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hongyuan Zhu","raw_affiliation_strings":["Institute for Infocomm Research (I2R), Agency for Science, Technology, and Research (A*STAR), Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5177-8320","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Agency for Science, Technology, and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000892367","display_name":"Hancheng Ye","orcid":"https://orcid.org/0000-0002-6272-2792"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hancheng Ye","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127099402","display_name":"Yihang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihang Yang","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076278944","display_name":"Fukun Yin","orcid":"https://orcid.org/0000-0003-2623-1619"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fukun Yin","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2623-1619","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127194156","display_name":"Tao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Chen","raw_affiliation_strings":["School of Information Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0779-9818","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20896538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"5809","last_page":"5820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.266400009393692,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.266400009393692,"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"}},{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.08209999650716782,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.056299999356269836,"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/generative-grammar","display_name":"Generative grammar","score":0.616599977016449},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5580999851226807},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5497999787330627},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5485000014305115},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.51419997215271},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5023000240325928},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.492900013923645},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4837999939918518},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4650000035762787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8532000184059143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.664900004863739},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.616599977016449},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5580999851226807},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5497999787330627},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5485000014305115},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.51419997215271},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.492900013923645},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4837999939918518},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44179999828338623},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3928000032901764},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.37540000677108765},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3264000117778778},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3249000012874603},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3172999918460846},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2533000111579895},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3668488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668488","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/G3977413633","display_name":"\u5b50\u7c7b\u611f\u77e5\u6df1\u5ea6\u5b66\u4e60\u7406\u8bba\u53ca\u5176\u5e94\u7528\u7814\u7a76","funder_award_id":"62071127","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5491202952","display_name":"\u9762\u5411\u6709\u9650\u7b97\u529b\u548c\u6570\u636e\u8d44\u6e90\u7684\u591a\u6a21\u6001\u878d\u5408\u4e0e\u77e5\u8bc6\u63a8\u7406\u7814\u7a76","funder_award_id":"23ZR1402900","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"},{"id":"https://openalex.org/G7626924423","display_name":null,"funder_award_id":"62101137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,13,60,89,190],"multi-object":[1,189],"visual":[2],"grounding":[3,105,178,191],"aims":[4],"to":[5,17,41,103,118,137],"identify":[6],"and":[7,46,57,85,124,166,173,192],"localize":[8],"all":[9],"objects":[10,170],"in":[11,55,63,188,195,202],"a":[12,18,81,108,115,159],"scene":[14,121,128],"that":[15,100,164,183],"correspond":[16],"given":[19],"text":[20,142],"description.":[21],"Unlike":[22],"traditional":[23,196],"single-object":[24,197],"grounding,":[25],"this":[26],"task":[27],"presents":[28],"additional":[29],"challenges":[30],"as":[31],"point":[32],"clouds":[33],"inherently":[34,53],"lack":[35],"fine-grained":[36,127],"details,":[37],"making":[38],"it":[39],"difficult":[40],"capture":[42,125],"subtle":[43],"object":[44,67],"features":[45,143],"contextual":[47],"information.":[48],"Moreover,":[49],"textual":[50],"descriptions":[51],"are":[52,171],"limited":[54],"perceiving":[56],"understanding":[58],"complex":[59],"environments,":[61],"especially":[62],"scenarios":[64],"with":[65],"high":[66],"similarity":[68],"or":[69],"intricate":[70],"spatial":[71,167],"arrangements.":[72],"To":[73],"tackle":[74],"the":[75,112,126,131,139,145,150,177],"above":[76],"challenges,":[77],"we":[78,157],"propose":[79],"SGMG,":[80],"Rendered":[82],"2D":[83],"Semantic":[84],"Generative":[86],"priors":[87],"guided":[88],"Multi-object":[90],"Grounding":[91],"Framework.":[92],"The":[93],"SGMG":[94,184],"framework":[95],"introduces":[96],"two":[97],"key":[98],"innovations":[99],"work":[101],"cohesively":[102],"enhance":[104],"accuracy.":[106],"First,":[107],"Generative-Assistant(GA)":[109],"Module":[110,134],"leverages":[111],"capabilities":[113],"of":[114,141,152],"generative":[116],"model":[117],"provide":[119],"enriched":[120],"prior":[122],"information":[123,154],"details.":[129],"Second,":[130],"Semantic-Augment":[132],"Fusion(SAF)":[133],"is":[135],"designed":[136],"improve":[138],"representation":[140],"from":[144],"vision":[146],"features,":[147],"thereby":[148],"boosting":[149],"accuracy":[151],"multimodal":[153],"interactions.":[155],"Furthermore,":[156],"introduce":[158],"multi-level":[160],"fusion":[161],"mechanism,":[162],"ensuring":[163],"semantic":[165],"relationships":[168],"between":[169],"preserved":[172],"effectively":[174],"leveraged":[175],"during":[176],"process.":[179],"Experimental":[180],"results":[181,194],"demonstrate":[182],"achieves":[185],"state-of-the-art":[186],"performance":[187],"competitive":[193],"tasks,":[198],"highlighting":[199],"its":[200],"effectiveness":[201],"diverse":[203],"scenarios.":[204]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-02-28T00:00:00"}