{"id":"https://openalex.org/W4285606658","doi":"https://doi.org/10.24963/ijcai.2022/194","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","display_name":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285606658","doi":"https://doi.org/10.24963/ijcai.2022/194"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/194","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/194","pdf_url":"https://www.ijcai.org/proceedings/2022/0194.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0194.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100453993","display_name":"Heng Wang","orcid":"https://orcid.org/0009-0009-5473-5751"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Heng Wang","raw_affiliation_strings":["University of Sydney","School of Computer Science, University of Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080719369","display_name":"Chaoyi Zhang","orcid":"https://orcid.org/0000-0001-8492-9711"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chaoyi Zhang","raw_affiliation_strings":["University of Sydney","School of Computer Science, University of Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109592999","display_name":"Jianhui Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jianhui Yu","raw_affiliation_strings":["University of Sydney","School of Computer Science, University of Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076697411","display_name":"Weidong Cai","orcid":"https://orcid.org/0000-0003-3706-8896"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weidong Cai","raw_affiliation_strings":["University of Sydney","School of Computer Science, University of Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100453993"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":1.7112,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.89557748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1393","last_page":"1400"},"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":0.9991999864578247,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9911999702453613,"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":0.8201342821121216},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7398097515106201},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6422091722488403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6357707381248474},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5675506591796875},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5645976662635803},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4849124550819397},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.4750768542289734},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.46315398812294006},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4538780450820923},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42047178745269775},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35515743494033813},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3341436982154846},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14561453461647034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8201342821121216},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7398097515106201},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6422091722488403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6357707381248474},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5675506591796875},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5645976662635803},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4849124550819397},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4750768542289734},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.46315398812294006},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4538780450820923},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42047178745269775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35515743494033813},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3341436982154846},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14561453461647034},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/194","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/194","pdf_url":"https://www.ijcai.org/proceedings/2022/0194.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/194","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/194","pdf_url":"https://www.ijcai.org/proceedings/2022/0194.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285606658.pdf","grobid_xml":"https://content.openalex.org/works/W4285606658.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1956340063","https://openalex.org/W2032846947","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2250539671","https://openalex.org/W2552002300","https://openalex.org/W2594519801","https://openalex.org/W2903435684","https://openalex.org/W2903617461","https://openalex.org/W2950784811","https://openalex.org/W2963121255","https://openalex.org/W2963758027","https://openalex.org/W2964062501","https://openalex.org/W2976658881","https://openalex.org/W2979987972","https://openalex.org/W2988715931","https://openalex.org/W2990818246","https://openalex.org/W3015373178","https://openalex.org/W3034655362","https://openalex.org/W3095974555","https://openalex.org/W3096609285","https://openalex.org/W3107521863","https://openalex.org/W3173271937","https://openalex.org/W3174377922","https://openalex.org/W3182910454","https://openalex.org/W3193171560","https://openalex.org/W3203949114","https://openalex.org/W4238700468","https://openalex.org/W4287553517","https://openalex.org/W4288329833","https://openalex.org/W4295312788","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Dense":[0],"captioning":[1,34],"in":[2,27,65,97,143],"3D":[3,13,29,32,98],"point":[4],"clouds":[5],"is":[6,155],"an":[7,113],"emerging":[8],"vision-and-language":[9],"task":[10],"involving":[11],"object-level":[12],"scene":[14,56],"understanding.":[15],"Apart":[16],"from":[17],"coarse":[18],"semantic":[19],"class":[20],"prediction":[21],"and":[22,40,51,62,100,112,118,129,141,152],"bounding":[23],"box":[24],"regression":[25],"as":[26],"traditional":[28],"object":[30,57,120],"detection,":[31],"dense":[33],"aims":[35],"at":[36,157],"producing":[37],"a":[38,66,77,102,106],"further":[39],"finer":[41],"instance-level":[42],"label":[43],"of":[44,58,71,95],"natural":[45],"language":[46],"description":[47],"on":[48,124],"visual":[49],"appearance":[50],"spatial":[52,108],"relations":[53],"for":[54,116],"each":[55],"interest.":[59],"To":[60],"detect":[61],"describe":[63],"objects":[64,85,96],"scene,":[67],"following":[68],"the":[69,92,135],"spirit":[70],"neural":[72],"machine":[73],"translation,":[74],"we":[75,89],"propose":[76],"transformer-based":[78],"encoder-decoder":[79],"architecture,":[80],"namely":[81],"SpaCap3D,":[82],"to":[83],"transform":[84],"into":[86],"descriptions,":[87],"where":[88],"especially":[90],"investigate":[91],"relative":[93],"spatiality":[94],"scenes":[99],"design":[101],"spatiality-guided":[103],"encoder":[104],"via":[105],"token-to-token":[107],"relation":[109],"learning":[110],"objective":[111],"object-centric":[114],"decoder":[115],"precise":[117],"spatiality-enhanced":[119],"caption":[121],"generation.":[122],"Evaluated":[123],"two":[125],"benchmark":[126],"datasets,":[127],"ScanRefer":[128],"ReferIt3D,":[130],"our":[131],"proposed":[132],"SpaCap3D":[133],"outperforms":[134],"baseline":[136],"method":[137],"Scan2Cap":[138],"by":[139],"4.94%":[140],"9.61%":[142],"CIDEr@0.5IoU,":[144],"respectively.":[145],"Our":[146],"project":[147],"page":[148],"with":[149],"source":[150],"code":[151],"supplementary":[153],"files":[154],"available":[156],"https://SpaCap3D.github.io/.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":7}],"updated_date":"2026-05-25T08:39:21.599409","created_date":"2025-10-10T00:00:00"}