{"id":"https://openalex.org/W4389520041","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.56","title":"ARKitSceneRefer: Text-based Localization of Small Objects in Diverse Real-World 3D Indoor Scenes","display_name":"ARKitSceneRefer: Text-based Localization of Small Objects in Diverse Real-World 3D Indoor Scenes","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389520041","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.56"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.56","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.56","pdf_url":"https://aclanthology.org/2023.findings-emnlp.56.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.findings-emnlp.56.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101894980","display_name":"Shunya Kato","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shunya Kato","raw_affiliation_strings":["Kyoto University"],"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073732915","display_name":"Shuhei Kurita","orcid":"https://orcid.org/0000-0001-7415-3120"},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shuhei Kurita","raw_affiliation_strings":["RIKEN"],"affiliations":[{"raw_affiliation_string":"RIKEN","institution_ids":["https://openalex.org/I4210110652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":["Kyoto University"],"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028836340","display_name":"Sadao Kurohashi","orcid":"https://orcid.org/0000-0001-5398-8399"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sadao Kurohashi","raw_affiliation_strings":["Kyoto University"],"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101894980"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":0.1185,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44299024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"784","last_page":"799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9991000294685364,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.7938947677612305},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7228102684020996},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6790832877159119},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.6294772624969482},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5949327945709229},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5915156602859497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5385203957557678},{"id":"https://openalex.org/keywords/doors","display_name":"Doors","score":0.5033501982688904},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.4625987112522125},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4031202495098114},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3888988196849823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7938947677612305},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7228102684020996},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6790832877159119},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.6294772624969482},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5949327945709229},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5915156602859497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5385203957557678},{"id":"https://openalex.org/C125209513","wikidata":"https://www.wikidata.org/wiki/Q4037520","display_name":"Doors","level":2,"score":0.5033501982688904},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.4625987112522125},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4031202495098114},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3888988196849823},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.findings-emnlp.56","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.56","pdf_url":"https://aclanthology.org/2023.findings-emnlp.56.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.56","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.56","pdf_url":"https://aclanthology.org/2023.findings-emnlp.56.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G3291250701","display_name":null,"funder_award_id":"KAKENHI","funder_id":"https://openalex.org/F4320338111","funder_display_name":"Precursory Research for Embryonic Science and Technology"},{"id":"https://openalex.org/G518326379","display_name":"Creation of datasets that combine 3D environmental and textual information","funder_award_id":"22K17983","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5506463476","display_name":null,"funder_award_id":"JP22K1","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6042280714","display_name":null,"funder_award_id":"JP22K17983","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4389520041.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1673310716","https://openalex.org/W1773149199","https://openalex.org/W1889081078","https://openalex.org/W2250539671","https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2557465155","https://openalex.org/W2594519801","https://openalex.org/W2747053578","https://openalex.org/W2908510526","https://openalex.org/W2948672349","https://openalex.org/W2949830259","https://openalex.org/W2953320089","https://openalex.org/W2963109634","https://openalex.org/W2963521717","https://openalex.org/W2964339842","https://openalex.org/W2981422075","https://openalex.org/W2981663434","https://openalex.org/W3034578524","https://openalex.org/W3045491541","https://openalex.org/W3095974555","https://openalex.org/W3096609285","https://openalex.org/W3107521863","https://openalex.org/W3126391825","https://openalex.org/W3133833192","https://openalex.org/W3159619744","https://openalex.org/W3203949114","https://openalex.org/W4200629315","https://openalex.org/W4225517085","https://openalex.org/W4225539092","https://openalex.org/W4226023638","https://openalex.org/W4226376247","https://openalex.org/W4281633595","https://openalex.org/W4284675794","https://openalex.org/W4285192809","https://openalex.org/W4286973470","https://openalex.org/W4298187165","https://openalex.org/W4312424618","https://openalex.org/W4312649925","https://openalex.org/W4312749817","https://openalex.org/W4312956471","https://openalex.org/W4313068342","https://openalex.org/W4313162371","https://openalex.org/W4379961490","https://openalex.org/W4386148478"],"related_works":["https://openalex.org/W3016239942","https://openalex.org/W2486091485","https://openalex.org/W4293365988","https://openalex.org/W2374188760","https://openalex.org/W2997934945","https://openalex.org/W2468876127","https://openalex.org/W4205206412","https://openalex.org/W2885750329","https://openalex.org/W2373862202","https://openalex.org/W2388232445"],"abstract_inverted_index":{"3D":[0,14,40,81,120,141],"referring":[1,41,121,143],"expression":[2,42,144],"comprehension":[3,43,145],"is":[4,17],"a":[5,18],"task":[6,20,150],"to":[7,29,33,53],"ground":[8],"text":[9],"representations":[10],"onto":[11],"objects":[12,31,95,106],"in":[13,34,99,155],"scenes.":[15,102],"It":[16],"crucial":[19],"for":[21],"indoor":[22,39,101,109],"household":[23],"robots":[24],"or":[25,59,70],"augmented":[26],"reality":[27],"devices":[28],"localize":[30],"referred":[32],"user":[35],"instructions.":[36],"However,":[37],"existing":[38,119],"datasets":[44],"typically":[45],"cover":[46],"larger":[47,114],"object":[48,126,159],"classes":[49,127],"that":[50,96],"are":[51,112],"easy":[52],"localize,":[54],"such":[55,66],"as":[56,67],"chairs,":[57],"tables,":[58],"doors,":[60],"and":[61,79,123,140],"often":[62],"overlook":[63],"small":[64,93,158],"objects,":[65],"cooking":[68],"tools":[69],"office":[71],"supplies.":[72],"Based":[73],"on":[74,92],"the":[75,88,118,131,149,153,156],"recently":[76],"proposed":[77],"diverse":[78,125,157],"high-resolution":[80],"scene":[82],"dataset":[83,90],"of":[84,107,117,128,152],"ARKitScenes,":[85],"we":[86,147],"construct":[87],"ARKitSceneRefer":[89,103],"focusing":[91],"daily-use":[94],"frequently":[97],"appear":[98],"real-world":[100],"contains":[104],"15k":[105],"1,605":[108],"scenes,":[110],"which":[111],"significantly":[113],"than":[115],"those":[116],"datasets,":[122],"covers":[124],"583":[129],"from":[130],"LVIS":[132],"dataset.":[133],"In":[134],"empirical":[135],"experiments":[136],"with":[137],"both":[138],"2D":[139],"state-of-the-art":[142],"models,":[146],"observed":[148],"difficulty":[151],"localization":[154],"classes.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}