{"id":"https://openalex.org/W4403792400","doi":"https://doi.org/10.1145/3664647.3680758","title":"Advancing 3D Object Grounding Beyond a Single 3D Scene","display_name":"Advancing 3D Object Grounding Beyond a Single 3D Scene","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792400","doi":"https://doi.org/10.1145/3664647.3680758"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680758","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5072986859","display_name":"Wencan Huang","orcid":"https://orcid.org/0000-0002-1555-3674"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wencan Huang","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1555-3674","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078220957","display_name":"Daizong Liu","orcid":"https://orcid.org/0000-0001-8179-4508"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daizong Liu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8179-4508","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059045087","display_name":"Wei Hu","orcid":"https://orcid.org/0000-0002-9860-0922"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Hu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9860-0922","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072986859"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.508,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89280407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7995","last_page":"8004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9994999766349792,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9987000226974487,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6384631395339966},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.618449866771698},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.49331966042518616},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4561670422554016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42530661821365356},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.40048396587371826},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14365985989570618},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09466424584388733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6384631395339966},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.618449866771698},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.49331966042518616},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4561670422554016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42530661821365356},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.40048396587371826},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14365985989570618},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09466424584388733}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680758","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":50,"referenced_works":["https://openalex.org/W1966601141","https://openalex.org/W2166821106","https://openalex.org/W2296073425","https://openalex.org/W2298532145","https://openalex.org/W2594519801","https://openalex.org/W2962849746","https://openalex.org/W2972640707","https://openalex.org/W2988715931","https://openalex.org/W2999905431","https://openalex.org/W3034949383","https://openalex.org/W3035232877","https://openalex.org/W3035666869","https://openalex.org/W3039991645","https://openalex.org/W3101633331","https://openalex.org/W3133833192","https://openalex.org/W3140398265","https://openalex.org/W3173349970","https://openalex.org/W3174178235","https://openalex.org/W3175234951","https://openalex.org/W3179868941","https://openalex.org/W3202242435","https://openalex.org/W3203949114","https://openalex.org/W3206171352","https://openalex.org/W4207072548","https://openalex.org/W4211092666","https://openalex.org/W4214526701","https://openalex.org/W4214684415","https://openalex.org/W4214773923","https://openalex.org/W4221145551","https://openalex.org/W4242177601","https://openalex.org/W4310286406","https://openalex.org/W4312274934","https://openalex.org/W4312385518","https://openalex.org/W4312565984","https://openalex.org/W4312749817","https://openalex.org/W4312852845","https://openalex.org/W4313162371","https://openalex.org/W4313639403","https://openalex.org/W4386065895","https://openalex.org/W4386066792","https://openalex.org/W4386075583","https://openalex.org/W4386075724","https://openalex.org/W4386076585","https://openalex.org/W4386794361","https://openalex.org/W4387969417","https://openalex.org/W4390871962","https://openalex.org/W4390872495","https://openalex.org/W4390874439","https://openalex.org/W4390874680","https://openalex.org/W4403791871"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"As":[0],"a":[1,12,17,22,28,42,47,54,83,95,102,152,157,177,198,219,230],"widely":[2],"explored":[3],"multi-modal":[4,243],"task,":[5],"3D":[6,19,49,57,89,99,134,162,172,215,285],"object":[7,15,44,70,173,286],"grounding":[8,163,174,287],"endeavors":[9],"to":[10,39,92,108,142,185,205,217,264],"localize":[11],"unique":[13],"pre-existing":[14],"within":[16,136],"single":[18],"scene":[20,120,216],"given":[21],"natural":[23],"language":[24],"description.":[25],"However,":[26],"such":[27],"strict":[29],"setting":[30,281],"is":[31,35,59,203,224],"unnatural":[32],"as":[33],"it":[34],"not":[36,66],"always":[37],"possible":[38],"know":[40],"whether":[41],"target":[43,76,106,116,211],"exists":[45],"in":[46,110,118,131,164,213],"specific":[48],"scene.":[50,112],"In":[51],"real-world":[52],"scenarios,":[53],"collection":[55],"of":[56,63,97,105,114,210,249],"scenes":[58,135],"generally":[60],"available,":[61],"some":[62,72],"which":[64,168,223],"may":[65,140],"contain":[67,74],"the":[68,126,137,165,170,188,207,241,247,250,257,279,283],"described":[69],"while":[71],"potentially":[73],"multiple":[75],"objects.":[77],"To":[78,145,245],"this":[79],"end,":[80],"we":[81,122,150,253],"introduce":[82],"more":[84,147],"realistic":[85],"setting,":[86,167],"named":[87,155],"Group-wise":[88],"Object":[90],"Grounding,":[91],"simultaneously":[93],"process":[94],"group":[96,139],"related":[98,133],"scenes,":[100],"allowing":[101],"flexible":[103],"number":[104],"objects":[107,117,212],"exist":[109],"each":[111,119,214],"Instead":[113],"localizing":[115],"individually,":[121],"argue":[123],"that":[124,273],"ignoring":[125],"rich":[127],"visual":[128,190,208,220,237],"information":[129],"contained":[130],"other":[132],"same":[138],"lead":[141],"sub-optimal":[143],"results.":[144],"achieve":[146],"accurate":[148],"localization,":[149],"propose":[151,261],"baseline":[153],"method":[154],"GNL3D,":[156],"Grouped":[158],"Neural":[159],"Listener":[160],"for":[161,235],"group-wise":[166,280],"extends":[169],"traditional":[171,284],"pipeline":[175],"with":[176],"novel":[178],"language-guided":[179,199],"consensus":[180,200,221],"aggregation":[181,201],"and":[182,227,255,260,268,282],"distribution":[183],"mechanism":[184],"explicitly":[186],"exploit":[187],"intra-group":[189],"connections.":[191],"Specifically,":[192],"based":[193],"on":[194,278],"context-aware":[195],"spatial-semantic":[196],"alignment,":[197],"module":[202,234],"developed":[204],"aggregate":[206],"features":[209],"form":[218],"representation,":[222],"then":[225],"distributed":[226],"injected":[228],"into":[229],"consensus-modulated":[231],"feature":[232],"refinement":[233],"refining":[236],"features,":[238],"thus":[239],"benefiting":[240],"subsequent":[242],"reasoning.":[244],"validate":[246],"effectiveness":[248],"proposed":[251],"method,":[252],"reorganize":[254],"enhance":[256],"ReferIt3D":[258],"dataset":[259],"evaluation":[262],"metrics":[263],"benchmark":[265],"prior":[266],"work":[267],"GNL3D.":[269],"Extensive":[270],"experiments":[271],"demonstrate":[272],"GNL3D":[274],"achieves":[275],"state-of-the-art":[276],"results":[277],"task.":[288]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}