{"id":"https://openalex.org/W4413925860","doi":"https://doi.org/10.1109/icra55743.2025.11127295","title":"3DWG: 3D Weakly Supervised Visual Grounding via Category and Instance-Level Alignment","display_name":"3DWG: 3D Weakly Supervised Visual Grounding via Category and Instance-Level Alignment","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925860","doi":"https://doi.org/10.1109/icra55743.2025.11127295"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5100634697","display_name":"Xiaoqi Li","orcid":"https://orcid.org/0000-0001-7462-6303"},"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":"Xiaoqi Li","raw_affiliation_strings":["School of CS, Peking University"],"affiliations":[{"raw_affiliation_string":"School of CS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046817911","display_name":"Jiaming Liu","orcid":"https://orcid.org/0000-0002-6770-4390"},"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":"Jiaming Liu","raw_affiliation_strings":["School of CS, Peking University"],"affiliations":[{"raw_affiliation_string":"School of CS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103392540","display_name":"Nuowei Han","orcid":null},"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":"Nuowei Han","raw_affiliation_strings":["School of CS, Peking University"],"affiliations":[{"raw_affiliation_string":"School of CS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100573304","display_name":"Liang Heng","orcid":"https://orcid.org/0009-0002-8205-6747"},"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":"Liang Heng","raw_affiliation_strings":["School of CS, Peking University"],"affiliations":[{"raw_affiliation_string":"School of CS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038064028","display_name":"Yandong Guo","orcid":"https://orcid.org/0000-0002-4594-8415"},"institutions":[{"id":"https://openalex.org/I4210136571","display_name":"Medrobotics (United States)","ror":"https://ror.org/03z02zc05","country_code":"US","type":"company","lineage":["https://openalex.org/I4210136571"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yandong Guo","raw_affiliation_strings":["AI2Robotic"],"affiliations":[{"raw_affiliation_string":"AI2Robotic","institution_ids":["https://openalex.org/I4210136571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389349","display_name":"Dong Hao","orcid":"https://orcid.org/0000-0002-1476-2861"},"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":"Hao Dong","raw_affiliation_strings":["School of CS, Peking University"],"affiliations":[{"raw_affiliation_string":"School of CS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351175","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0003-4242-4840"},"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":"Yang Liu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100634697"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.6381,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91537177,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"12766","last_page":"12773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9983999729156494,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9983999729156494,"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":0.9976000189781189,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.611197292804718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5485110282897949},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5261722803115845},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39597374200820923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3292539715766907},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11549645662307739},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.057430803775787354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.611197292804718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485110282897949},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5261722803115845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39597374200820923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3292539715766907},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11549645662307739},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.057430803775787354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3077714275","display_name":null,"funder_award_id":"62372014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3701923927","display_name":null,"funder_award_id":"4252040","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2251329024","https://openalex.org/W2594519801","https://openalex.org/W2963445828","https://openalex.org/W2963536419","https://openalex.org/W2963614783","https://openalex.org/W2989176720","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3117585461","https://openalex.org/W3133833192","https://openalex.org/W3175234951","https://openalex.org/W3178418424","https://openalex.org/W3179041377","https://openalex.org/W3203949114","https://openalex.org/W3206171352","https://openalex.org/W4206725542","https://openalex.org/W4214526701","https://openalex.org/W4214684415","https://openalex.org/W4312660311","https://openalex.org/W4312749817","https://openalex.org/W4312852845","https://openalex.org/W4389519030","https://openalex.org/W4390871962","https://openalex.org/W4390873695","https://openalex.org/W4393148022","https://openalex.org/W4401415839","https://openalex.org/W4401416853","https://openalex.org/W4401417232","https://openalex.org/W4402660158","https://openalex.org/W4402703117","https://openalex.org/W4402727708","https://openalex.org/W4402727730","https://openalex.org/W4402754162","https://openalex.org/W4402754253","https://openalex.org/W4402778219","https://openalex.org/W4403002335"],"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":{"The":[0],"3D":[1,10],"weakly-supervised":[2],"visual":[3],"grounding":[4,86],"task":[5],"aims":[6],"to":[7,23,73,109,134,149,162],"localize":[8],"oriented":[9],"boxes":[11],"in":[12,47,69],"point":[13,51],"clouds":[14],"based":[15],"on":[16,170],"natural":[17],"language":[18,132],"descriptions":[19,130],"without":[20],"requiring":[21],"annotations":[22],"guide":[24],"model":[25,148],"learning.":[26],"This":[27],"setting":[28],"presents":[29],"two":[30],"primary":[31],"challenges:":[32],"category-level":[33,97],"ambiguity":[34,39],"and":[35,93,177],"instance-level":[36,124],"complexity.":[37],"Category-level":[38],"arises":[40],"from":[41,61,104,131],"representing":[42],"objects":[43,153],"of":[44,64],"fine-grained":[45],"categories":[46,92],"a":[48,70,83,105],"highly":[49],"sparse":[50],"cloud":[52],"format,":[53],"making":[54],"category":[55,67,102,116,120],"distinction":[56],"challenging.":[57],"Instance-level":[58],"complexity":[59],"stems":[60],"multiple":[62],"instances":[63,156],"the":[65,96,123,158],"same":[66,159],"coexisting":[68],"scene,":[71],"leading":[72],"distractions":[74],"during":[75],"grounding.":[76],"To":[77],"address":[78],"these":[79],"challenges,":[80],"we":[81,99,126],"propose":[82],"novel":[84],"weaklysupervised":[85],"approach":[87,166],"that":[88],"explicitly":[89],"differentiates":[90],"between":[91],"instances.":[94],"In":[95,122],"branch,":[98,125],"utilize":[100,127],"extensive":[101],"knowledge":[103],"pre-trained":[106],"external":[107],"detector":[108],"align":[110],"object":[111,136],"proposal":[112,137],"features":[113],"with":[114],"sentencelevel":[115],"features,":[117,138],"thereby":[118],"enhancing":[119],"awareness.":[121],"spatial":[128],"relationship":[129],"queries":[133],"refine":[135],"ensuring":[139],"clear":[140],"differentiation":[141],"among":[142],"objects.":[143],"These":[144],"designs":[145],"enable":[146],"our":[147,165],"accurately":[150],"identify":[151],"target-category":[152],"while":[154],"distinguishing":[155],"within":[157],"category.":[160],"Compared":[161],"previous":[163],"methods,":[164],"achieves":[167],"state-of-the-art":[168],"performance":[169],"three":[171],"widely":[172],"used":[173],"benchmarks:":[174],"Nr3D,":[175],"Sr3D,":[176],"ScanRef.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}