{"id":"https://openalex.org/W4377707861","doi":"https://doi.org/10.1109/tvcg.2023.3279204","title":"Complete 3D Relationships Extraction Modality Alignment Network for 3D Dense Captioning","display_name":"Complete 3D Relationships Extraction Modality Alignment Network for 3D Dense Captioning","publication_year":2023,"publication_date":"2023-05-23","ids":{"openalex":"https://openalex.org/W4377707861","doi":"https://doi.org/10.1109/tvcg.2023.3279204","pmid":"https://pubmed.ncbi.nlm.nih.gov/37220037"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2023.3279204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2023.3279204","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5014555076","display_name":"Aihua Mao","orcid":"https://orcid.org/0000-0001-6861-9414"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aihua Mao","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6861-9414","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101561407","display_name":"Yang Zhi","orcid":"https://orcid.org/0000-0002-9768-2356"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Yang","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9768-2356","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wanxin Chen","orcid":"https://orcid.org/0009-0001-1611-4104"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanxin Chen","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-1611-4104","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054879013","display_name":"Ran Yi","orcid":"https://orcid.org/0000-0003-1858-3358"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Yi","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1858-3358","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008076279","display_name":"Yong\u2010Jin Liu","orcid":"https://orcid.org/0000-0001-5774-1916"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong-Jin Liu","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, MOE-Key Laboratory of Pervasive Computing, Tsinghua University, Beijing, China","BNRist, Department of Computer Science and Technology, MOE-Key Laboratory of Pervasive Computing, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5774-1916","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, MOE-Key Laboratory of Pervasive Computing, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"BNRist, Department of Computer Science and Technology, MOE-Key Laboratory of Pervasive Computing, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2345,"currency":"USD","value_usd":2345},"apc_paid":null,"fwci":0.9482,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.73028735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"30","issue":"8","first_page":"4867","last_page":"4880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9944999814033508,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8549290299415588},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8012595176696777},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.70762038230896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6525751352310181},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5026383399963379},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47385886311531067},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45973312854766846},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4503633975982666},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4179747700691223},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.41392937302589417},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4128771126270294},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4027900695800781},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2431003749370575}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8549290299415588},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8012595176696777},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.70762038230896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6525751352310181},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5026383399963379},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47385886311531067},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45973312854766846},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4503633975982666},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4179747700691223},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.41392937302589417},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4128771126270294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4027900695800781},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2431003749370575},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2023.3279204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2023.3279204","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:37220037","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37220037","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4183249293","display_name":null,"funder_award_id":"L222008","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G8058069278","display_name":null,"funder_award_id":"62272447","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2150824314","https://openalex.org/W2250539671","https://openalex.org/W2560645892","https://openalex.org/W2594519801","https://openalex.org/W2604729005","https://openalex.org/W2735305611","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2796426482","https://openalex.org/W2896457183","https://openalex.org/W2905544595","https://openalex.org/W2963091558","https://openalex.org/W2963743213","https://openalex.org/W2964078384","https://openalex.org/W2970231061","https://openalex.org/W2986670728","https://openalex.org/W2988715931","https://openalex.org/W3004349648","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3036900224","https://openalex.org/W3091588028","https://openalex.org/W3092820619","https://openalex.org/W3093319304","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3108319047","https://openalex.org/W3133833192","https://openalex.org/W3174377922","https://openalex.org/W3175234951","https://openalex.org/W3177430964","https://openalex.org/W3182910454","https://openalex.org/W3184743809","https://openalex.org/W3205071568","https://openalex.org/W3206171352","https://openalex.org/W3214042654","https://openalex.org/W4221167937","https://openalex.org/W4226376247","https://openalex.org/W4310463627","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6638523607","https://openalex.org/W6678262379","https://openalex.org/W6726873649","https://openalex.org/W6739778489","https://openalex.org/W6766904570","https://openalex.org/W6767211374"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"3D":[0,12,20,30,58,69,73,84,94,123,194],"dense":[1],"captioning":[2],"aims":[3],"to":[4,133,143,158,166,175],"semantically":[5],"describe":[6],"each":[7,110],"object":[8,70,111],"detected":[9],"in":[10,19,146,183],"a":[11,16,26,55,90,121],"scene,":[13],"which":[14,64],"plays":[15],"significant":[17],"role":[18],"scene":[21],"understanding.":[22],"Previous":[23],"works":[24],"lack":[25],"complete":[27,57,72,91,122],"definition":[28],"of":[29,66,93],"spatial":[31,85,95,100,107,136],"relationships":[32,74,124],"and":[33,38,76,104,112,131,139,163,187,210],"the":[34,43,46,83,98,105,113,141,153,168,172,176,180,184,193,200,204,208],"directly":[35],"integrate":[36],"visual":[37,173],"language":[39,177],"modalities,":[40],"thus":[41],"ignoring":[42],"discrepancies":[44],"between":[45,102,109],"two":[47],"modalities.":[48],"To":[49,80,116],"address":[50],"these":[51],"issues,":[52],"we":[53,88,119,151],"propose":[54,120,152],"novel":[56],"relationship":[59,86,101,108,137,161],"extraction":[60,125],"modality":[61,77,154],"alignment":[62,78,155],"network,":[63],"consists":[65],"three":[67],"steps:":[68],"detection,":[71],"extraction,":[75],"caption.":[79],"comprehensively":[81],"capture":[82],"features,":[87],"define":[89],"set":[92],"relationships,":[96],"including":[97],"local":[99],"objects":[103],"global":[106],"entire":[114],"scene.":[115,195],"this":[117],"end,":[118],"module":[126,157],"based":[127],"on":[128,207],"message":[129],"passing":[130],"self-attention":[132],"mine":[134],"multi-scale":[135,160],"features":[138,145,162],"inspect":[140],"transformation":[142],"obtain":[144],"different":[147],"views.":[148],"In":[149],"addition,":[150],"caption":[156],"fuse":[159],"generate":[164,189],"descriptions":[165,191],"bridge":[167],"semantic":[169],"gap":[170],"from":[171],"space":[174,178],"with":[179],"prior":[181],"information":[182],"word":[185],"embedding,":[186],"help":[188],"improved":[190],"for":[192],"Extensive":[196],"experiments":[197],"demonstrate":[198],"that":[199],"proposed":[201],"model":[202],"outperforms":[203],"state-of-the-art":[205],"methods":[206],"ScanRefer":[209],"Nr3D":[211],"datasets.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-08-31T07:19:18.363097","created_date":"2025-10-10T00:00:00"}