{"id":"https://openalex.org/W4415536929","doi":"https://doi.org/10.1145/3746027.3755497","title":"Dual Enhancement on 3D Vision-Language Perception for Monocular 3D Visual Grounding","display_name":"Dual Enhancement on 3D Vision-Language Perception for Monocular 3D Visual Grounding","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536929","doi":"https://doi.org/10.1145/3746027.3755497"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755497","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755497","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/A5025114241","display_name":"LI Yu-zhen","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhen Li","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0000-3540-0627","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343854","display_name":"Min Liu","orcid":"https://orcid.org/0000-0001-6406-4896"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Liu","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-6406-4896","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010816880","display_name":"\u5143 \u6e21\u8fba","orcid":"https://orcid.org/0000-0003-3995-4402"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Bian","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0003-3995-4402","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683380","display_name":"Xueping Wang","orcid":"https://orcid.org/0000-0003-4862-8975"},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueping Wang","raw_affiliation_strings":["College of Information Science and Engineering, Hunan Normal University, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0003-4862-8975","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan Normal University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057160246","display_name":"Zhaoyang Li","orcid":"https://orcid.org/0000-0003-4762-2993"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyang Li","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, HuNan, China"],"raw_orcid":"https://orcid.org/0000-0003-4762-2993","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, HuNan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100785866","display_name":"Gen Li","orcid":"https://orcid.org/0000-0001-6636-1106"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gen Li","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-6636-1106","affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113278407","display_name":"Yaonan Wang","orcid":"https://orcid.org/0009-0004-5365-6254"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaonan Wang","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0004-5365-6254","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]}],"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":0.32520798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4552","last_page":"4561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.9986000061035156,"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/monocular","display_name":"Monocular","score":0.5400000214576721},{"id":"https://openalex.org/keywords/equidistant","display_name":"Equidistant","score":0.47519999742507935},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47269999980926514},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4713999927043915},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.45019999146461487},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4011000096797943},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.3885999917984009},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.37950000166893005},{"id":"https://openalex.org/keywords/optical-illusion","display_name":"Optical illusion","score":0.37560001015663147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6732000112533569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6632000207901001},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5591999888420105},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C158245278","wikidata":"https://www.wikidata.org/wiki/Q4386982","display_name":"Equidistant","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47269999980926514},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3885999917984009},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C139793654","wikidata":"https://www.wikidata.org/wiki/Q174923","display_name":"Optical illusion","level":3,"score":0.37560001015663147},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.3492000102996826},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.3481000065803528},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C104319648","wikidata":"https://www.wikidata.org/wiki/Q1412040","display_name":"Figure\u2013ground","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2776694159","wikidata":"https://www.wikidata.org/wiki/Q351676","display_name":"Viewing angle","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C184047640","wikidata":"https://www.wikidata.org/wiki/Q182593","display_name":"Illusion","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755497","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755497","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":[{"id":"https://openalex.org/G8273347855","display_name":null,"funder_award_id":"62221002, 62425305, U22B205","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":27,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2962764817","https://openalex.org/W2962766617","https://openalex.org/W2963351448","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2987734933","https://openalex.org/W2999947750","https://openalex.org/W3006154882","https://openalex.org/W3035180028","https://openalex.org/W3093017735","https://openalex.org/W3095974555","https://openalex.org/W3110435696","https://openalex.org/W3159619744","https://openalex.org/W3173668541","https://openalex.org/W3179868941","https://openalex.org/W3203949114","https://openalex.org/W3215100485","https://openalex.org/W4200629618","https://openalex.org/W4312385518","https://openalex.org/W4312852845","https://openalex.org/W4313145013","https://openalex.org/W4322707256","https://openalex.org/W4395064954","https://openalex.org/W4402706555","https://openalex.org/W4403791264"],"related_works":[],"abstract_inverted_index":{"Monocular":[0],"3D":[1,12,85,98,106],"visual":[2],"grounding":[3],"is":[4],"a":[5,125,155,220],"novel":[6],"task":[7],"that":[8,35],"aims":[9],"to":[10,41,64,69,96,103,161,184],"locate":[11],"objects":[13],"in":[14,30,149,226],"RGB":[15],"images":[16],"using":[17],"text":[18,37,94,111,150,171,179],"descriptions":[19],"with":[20,61,116,219],"explicit":[21],"geometry":[22,28,114,190],"information.":[23],"Despite":[24],"the":[25,31,36,42,50,59,75,83,105,134,144,164,169,187,194,204,227],"inclusion":[26],"of":[27,44,87,108,136,146,189,224],"details":[29],"text,":[32],"we":[33,101,123,153],"observe":[34],"embeddings":[38,112],"are":[39,181],"sensitive":[40],"magnitude":[43],"numerical":[45],"values":[46],"but":[47],"largely":[48],"ignore":[49],"associated":[51],"measurement":[52],"units.":[53],"For":[54],"example,":[55],"simply":[56],"equidistant":[57],"mapping":[58,137],"length":[60,77],"unit":[62],"'meters'":[63],"'decimeters'":[65],"or":[66],"'centimeters'":[67],"leads":[68],"severe":[70],"performance":[71],"degradation,":[72],"even":[73],"though":[74],"physical":[76],"remains":[78],"equivalent.":[79],"This":[80],"observation":[81],"signifies":[82],"weak":[84],"comprehension":[86,135],"pre-trained":[88],"language":[89],"model,":[90],"which":[91,132],"generates":[92],"misguiding":[93],"features":[95,115,172,180],"hinder":[97],"perception.":[99],"Therefore,":[100],"propose":[102,154],"enhance":[104,163],"perception":[107],"model":[109],"on":[110,203],"and":[113,119,200],"two":[117],"simple":[118],"effective":[120],"methods.":[121],"Firstly,":[122],"introduce":[124],"pre-processing":[126],"method":[127,196],"named":[128],"3D-text":[129,165],"Enhancement":[130,158],"(3DTE),":[131],"enhances":[133],"relationships":[138],"between":[139],"different":[140],"units":[141],"by":[142,167],"augmenting":[143],"diversity":[145],"distance":[147],"descriptors":[148],"queries.":[151],"Next,":[152],"Text-Guided":[156],"Geometry":[157],"(TGE)":[159],"module":[160],"further":[162],"information":[166],"projecting":[168],"basic":[170],"into":[173],"geometrically":[174],"consistent":[175],"space.":[176],"These":[177],"3D-enhanced":[178],"then":[182],"leveraged":[183],"precisely":[185],"guide":[186],"attention":[188],"features.":[191],"We":[192],"evaluate":[193],"proposed":[195],"through":[197],"extensive":[198],"comparisons":[199],"ablation":[201],"studies":[202],"Mono3DRefer":[205],"dataset.":[206],"Experimental":[207],"results":[208,218],"demonstrate":[209],"substantial":[210],"improvements":[211],"over":[212],"previous":[213],"methods,":[214],"achieving":[215],"new":[216],"state-of-the-art":[217],"notable":[221],"accuracy":[222],"gain":[223],"11.94%":[225],"'Far'":[228],"scenario.":[229],"Our":[230],"code":[231],"will":[232],"be":[233],"made":[234],"publicly":[235],"available.":[236]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}