{"id":"https://openalex.org/W4401414578","doi":"https://doi.org/10.1109/icra57147.2024.10610779","title":"OpenAnnotate3D: Open-Vocabulary Auto-Labeling System for Multi-modal 3D Data","display_name":"OpenAnnotate3D: Open-Vocabulary Auto-Labeling System for Multi-modal 3D Data","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414578","doi":"https://doi.org/10.1109/icra57147.2024.10610779"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5044411958","display_name":"Yijie Zhou","orcid":"https://orcid.org/0000-0003-0017-3107"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yijie Zhou","raw_affiliation_strings":["Fudan University,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023644455","display_name":"Likun Cai","orcid":"https://orcid.org/0000-0002-6052-9729"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Likun Cai","raw_affiliation_strings":["University of Toronto,Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto,Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051869626","display_name":"Xianhui Cheng","orcid":"https://orcid.org/0000-0002-4108-2124"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianhui Cheng","raw_affiliation_strings":["Fudan University,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103267605","display_name":"Zhongxue Gan","orcid":"https://orcid.org/0000-0003-2709-6148"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongxue Gan","raw_affiliation_strings":["Fudan University,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Xue","raw_affiliation_strings":["Fudan University,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018297466","display_name":"Wenchao Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenchao Ding","raw_affiliation_strings":["Fudan University,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5044411958"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":3.5963,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93626166,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9086","last_page":"9092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.996999979019165,"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":0.996999979019165,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9918000102043152,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.989799976348877,"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":0.7545427083969116},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6838276386260986},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5707598924636841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46842634677886963},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3837094306945801},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10289329290390015},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.054083675146102905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545427083969116},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6838276386260986},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5707598924636841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46842634677886963},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3837094306945801},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10289329290390015},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.054083675146102905},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1506491340","https://openalex.org/W1861492603","https://openalex.org/W1996688648","https://openalex.org/W2108598243","https://openalex.org/W2110764733","https://openalex.org/W2115579991","https://openalex.org/W2769833683","https://openalex.org/W2795276939","https://openalex.org/W2805292526","https://openalex.org/W2964216646","https://openalex.org/W2981630388","https://openalex.org/W2991216808","https://openalex.org/W2991375205","https://openalex.org/W3101577715","https://openalex.org/W4224308101","https://openalex.org/W4283026156","https://openalex.org/W4292779060","https://openalex.org/W4383109306","https://openalex.org/W4386065742","https://openalex.org/W4386067019","https://openalex.org/W4390874575","https://openalex.org/W4404612908","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6810081322","https://openalex.org/W6838461927","https://openalex.org/W6847363464","https://openalex.org/W6850787431"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0,54],"the":[1,87,96,104,113,135],"era":[2],"of":[3,16,90,99,106,112],"big":[4],"data":[5,14],"and":[6,27,73,80,95,128],"large":[7],"models,":[8],"automatic":[9],"annotating":[10],"functions":[11],"for":[12,19,50,78,116],"multi-modal":[13,51,118],"are":[15,45],"great":[17],"significance":[18],"real-world":[20,130],"AI-driven":[21],"applications,":[22],"such":[23],"as":[24],"autonomous":[25],"driving":[26],"embodied":[28],"AI.":[29],"Unlike":[30],"traditional":[31],"closed-set":[32],"annotation,":[33],"open-vocabulary":[34,47,62,117,148],"annotation":[35,139,144],"is":[36,110],"essential":[37],"to":[38,142],"achieve":[39],"human-level":[40],"cognition":[41],"capability.":[42],"However,":[43],"there":[44],"few":[46],"auto-labeling":[48,63],"systems":[49],"3D":[52,71,74,119],"data.":[53,83],"this":[55],"paper,":[56],"we":[57],"introduce":[58],"OpenAnnotate3D,":[59],"an":[60],"open-source":[61],"system":[64,85,136],"that":[65,134],"can":[66],"automatically":[67],"generate":[68],"2D":[69],"masks,":[70,72],"bounding":[75],"box":[76],"annotations":[77],"vision":[79],"point":[81],"cloud":[82],"Our":[84],"integrates":[86],"chain-of-thought":[88],"capabilities":[89,98],"Large":[91],"Language":[92],"Models":[93],"(LLMs)":[94],"cross-modality":[97],"vision-language":[100],"models":[101],"(VLMs).":[102],"To":[103],"best":[105],"our":[107],"knowledge,":[108],"OpenAnnotate3D":[109],"one":[111],"pioneering":[114],"works":[115],"auto-labeling.":[120],"We":[121],"conduct":[122],"comprehensive":[123],"evaluations":[124],"on":[125],"both":[126],"public":[127],"in-house":[129],"datasets,":[131],"which":[132],"demonstrate":[133],"significantly":[137],"improves":[138],"efficiency":[140],"compared":[141],"manual":[143],"while":[145],"providing":[146],"accurate":[147],"auto-annotating":[149],"results.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}