{"id":"https://openalex.org/W4415536393","doi":"https://doi.org/10.1145/3746027.3755836","title":"TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP","display_name":"TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536393","doi":"https://doi.org/10.1145/3746027.3755836"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755836","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5092125906","display_name":"Fan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Li","raw_affiliation_strings":["SGIT AI Lab, State Grid Corporation of China, Xi'an, China and Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0009-9658-2378","affiliations":[{"raw_affiliation_string":"SGIT AI Lab, State Grid Corporation of China, Xi'an, China and Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072795004","display_name":"Z Z Wang","orcid":"https://orcid.org/0009-0004-3726-6029"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zanyi Wang","raw_affiliation_strings":["SGIT AI Lab, State Grid Corporation of China, Xi'an, China and Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0004-3726-6029","affiliations":[{"raw_affiliation_string":"SGIT AI Lab, State Grid Corporation of China, Xi'an, China and Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110608354","display_name":"Zeyi Huang","orcid":"https://orcid.org/0009-0009-5897-2172"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyi Huang","raw_affiliation_strings":["Huawei, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-5897-2172","affiliations":[{"raw_affiliation_string":"Huawei, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102152323","display_name":"Guang Dai","orcid":"https://orcid.org/0000-0002-3529-9087"},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Dai","raw_affiliation_strings":["SGIT AI Lab, State Grid Corporation of China, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-3529-9087","affiliations":[{"raw_affiliation_string":"SGIT AI Lab, State Grid Corporation of China, Xi'an, China","institution_ids":["https://openalex.org/I17442442"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075880303","display_name":"Jingdong Wang","orcid":"https://orcid.org/0000-0002-4888-4445"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4888-4445","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100429685","display_name":"Mengmeng Wang","orcid":"https://orcid.org/0000-0003-4035-0630"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengmeng Wang","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4035-0630","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5257","last_page":"5266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9998999834060669,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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":0.9988999962806702,"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/point-cloud","display_name":"Point cloud","score":0.5986999869346619},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5232999920845032},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5199999809265137},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4878000020980835},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4844000041484833},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46219998598098755},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.454800009727478},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.453000009059906},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42969998717308044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682999968528748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6869000196456909},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5986999869346619},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5720999836921692},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5232999920845032},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5199999809265137},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2515999972820282},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755836","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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":21,"referenced_works":["https://openalex.org/W2594519801","https://openalex.org/W2752782242","https://openalex.org/W2963125977","https://openalex.org/W2964339842","https://openalex.org/W2988715931","https://openalex.org/W3095974555","https://openalex.org/W3096609285","https://openalex.org/W3107521863","https://openalex.org/W3140398265","https://openalex.org/W3203949114","https://openalex.org/W4214684415","https://openalex.org/W4312385518","https://openalex.org/W4312629998","https://openalex.org/W4312818263","https://openalex.org/W4312852845","https://openalex.org/W4386075583","https://openalex.org/W4386076097","https://openalex.org/W4390189960","https://openalex.org/W4390872570","https://openalex.org/W4402727761","https://openalex.org/W4402733575"],"related_works":[],"abstract_inverted_index":{"3D":[0,13,26,43,68,90,209,235,244],"visual":[1,9,27,210,245],"grounding":[2,28,211,246],"allows":[3],"an":[4,207],"embodied":[5,23],"agent":[6],"to":[7,55,78,87,113,142,164,188,214],"understand":[8],"information":[10],"in":[11,47,233,242],"real-world":[12],"environments":[14],"based":[15],"on":[16,32,89],"human":[17],"instructions,":[18],"which":[19],"is":[20,162],"crucial":[21],"for":[22,35,67,92,179],"intelligence.":[24],"Existing":[25],"methods":[29,85],"typically":[30],"rely":[31],"separate":[33],"encoders":[34,91],"different":[36],"modalities":[37,117],"(e.g.,":[38],"RGB":[39],"images,":[40,119],"text,":[41,120],"and":[42,49,99,121,149,158,172,183,200,238],"point":[44,75,122,170],"clouds),":[45,123],"resulting":[46],"large":[48],"complex":[50],"models":[51,64],"that":[52],"are":[53],"inefficient":[54],"train.":[56],"While":[57],"some":[58],"approaches":[59],"use":[60],"pre-trained":[61,110],"2D":[62,79,109,131],"multi-modal":[63,111,186],"like":[65],"CLIP":[66,132],"tasks,":[69],"they":[70],"still":[71],"struggle":[72],"with":[73,135],"aligning":[74],"cloud":[76],"data":[77],"encoders.":[80],"As":[81],"a":[82,107,130,185,230,239],"result,":[83],"these":[84],"continue":[86],"depend":[88],"feature":[93,198],"extraction,":[94],"further":[95],"increasing":[96],"model":[97,134],"complexity":[98],"training":[100],"inefficiency.":[101],"In":[102],"this":[103,138],"paper,":[104],"we":[105],"propose":[106],"unified":[108,197],"network":[112],"process":[114],"all":[115],"three":[116,204],"(RGB":[118],"significantly":[124],"simplifying":[125],"the":[126,143,203,215,220,234,243],"architecture.":[127],"By":[128],"leveraging":[129],"bi-modal":[133],"adapter-based":[136],"fine-tuning,":[137],"framework":[139],"effectively":[140],"adapts":[141],"tri-modal":[144],"setting,":[145],"improving":[146],"both":[147],"adaptability":[148],"performance":[150],"across":[151,202],"modalities.":[152],"Our":[153],"Geometric-Aware":[154],"2D-3D":[155],"Feature":[156],"Recovery":[157],"Fusion":[159],"(GARF)":[160],"module":[161],"designed":[163],"fuse":[165],"geometric":[166],"multi-scale":[167],"features":[168,178],"from":[169],"clouds":[171],"images.":[173],"We":[174],"then":[175],"integrate":[176],"textual":[177],"final":[180],"modality":[181],"fusion":[182,201],"introduce":[184],"decoder":[187],"facilitate":[189],"deep":[190],"cross-modal":[191],"understanding.":[192],"Together,":[193],"our":[194,217],"method":[195,218],"achieves":[196],"extraction":[199],"modalities,":[205],"enabling":[206],"end-to-end":[208],"model.":[212],"Compared":[213],"baseline,":[216],"reduces":[219],"number":[221],"of":[222],"trainable":[223],"parameters":[224],"by":[225],"approximately":[226],"58%,":[227],"while":[228],"achieving":[229],"6.52%":[231],"improvement":[232,241],"detection":[236],"task":[237],"6.25%":[240],"task.":[247]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}