{"id":"https://openalex.org/W4414360123","doi":"https://doi.org/10.24963/ijcai.2025/117","title":"DDPA-3DVG: Vision-Language Dual-Decoupling and Progressive Alignment for 3D Visual Grounding","display_name":"DDPA-3DVG: Vision-Language Dual-Decoupling and Progressive Alignment for 3D Visual Grounding","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360123","doi":"https://doi.org/10.24963/ijcai.2025/117"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/117","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5017933101","display_name":"Hongjie Gu","orcid":"https://orcid.org/0009-0006-8179-1829"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjie Gu","raw_affiliation_strings":["Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009068780","display_name":"Jinlong Fan","orcid":"https://orcid.org/0000-0002-0719-6486"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Fan","raw_affiliation_strings":["Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709340","display_name":"Liang Zheng","orcid":"https://orcid.org/0000-0002-1464-9500"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Zheng","raw_affiliation_strings":["Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345495","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0003-3512-8445"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112848590","display_name":"Yuxiang Yang","orcid":"https://orcid.org/0009-0007-7855-933X"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Yang","raw_affiliation_strings":["Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.21216519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1044","last_page":"1052"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9932000041007996,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9932000041007996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5245000123977661},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44209998846054077},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4120999872684479},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4068000018596649},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.38659998774528503},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.376800000667572},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33329999446868896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609000205993652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6912999749183655},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6658999919891357},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5245000123977661},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44209998846054077},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/117","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,103],"visual":[1,27,75],"grounding":[2],"aims":[3],"to":[4,61,119],"localize":[5],"target":[6,20,93],"objects":[7],"in":[8],"point":[9],"clouds":[10],"based":[11],"on":[12,43,130],"free-form":[13],"natural":[14,86],"language,":[15],"which":[16],"often":[17],"describes":[18],"both":[19],"and":[21,28,77,97,108,126,135],"reference":[22,95],"objects.":[23],"Effective":[24],"alignment":[25,125],"between":[26],"text":[29],"features":[30,45,57,116],"is":[31],"crucial":[32],"for":[33],"this":[34,64],"task.":[35],"However,":[36],"existing":[37],"two-stage":[38],"methods":[39,52],"that":[40,53,72],"rely":[41],"solely":[42],"object-level":[44],"can":[46,58],"yield":[47],"suboptimal":[48],"accuracy,":[49],"while":[50,101],"one-stage":[51],"align":[54],"only":[55],"point-level":[56,109],"be":[59,140],"prone":[60],"noise.":[62],"In":[63],"paper,":[65],"we":[66,84],"propose":[67],"DDPA-3DVG,":[68],"a":[69],"novel":[70],"framework":[71],"progressively":[73,112],"aligns":[74],"locations":[76],"language":[78,87],"descriptions":[79,88],"at":[80,142],"multiple":[81],"granularities.":[82],"Specifically,":[83],"decouple":[85],"into":[89,105],"distinct":[90],"representations":[91],"of":[92],"objects,":[94,96],"their":[98],"mutual":[99],"relationships,":[100],"disentangling":[102],"scenes":[104],"object-level,":[106],"voxel-level,":[107],"features.":[110],"By":[111],"fusing":[113],"these":[114],"dual-decoupled":[115],"from":[117],"coarse":[118],"fine,":[120],"our":[121],"method":[122],"enhances":[123],"cross-modal":[124],"achieves":[127],"state-of-the-art":[128],"performance":[129],"three":[131],"challenging":[132],"benchmarks\u2014ScanRefer,":[133],"Nr3D,":[134],"Sr3D.":[136],"The":[137],"code":[138],"will":[139],"released":[141],"https://github.com/HDU-VRLab/DDPA-3DVG.":[143]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}