{"id":"https://openalex.org/W4401634890","doi":"https://doi.org/10.1109/tmm.2024.3443670","title":"Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-Labeling","display_name":"Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-Labeling","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401634890","doi":"https://doi.org/10.1109/tmm.2024.3443670"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3443670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3443670","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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/A5100407860","display_name":"Xu Wang","orcid":"https://orcid.org/0000-0002-2948-6468"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Wang","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427026","display_name":"Yifan Li","orcid":"https://orcid.org/0000-0001-8880-3112"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Li","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055435177","display_name":"Qiudan Zhang","orcid":"https://orcid.org/0000-0001-6067-8188"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiudan Zhang","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081114494","display_name":"Wenhui Wu","orcid":"https://orcid.org/0000-0002-0416-7719"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhui Wu","raw_affiliation_strings":["College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037374554","display_name":"Mark Junjie Li","orcid":"https://orcid.org/0000-0002-7252-5346"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mark Junjie Li","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017116858","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-7331-6132"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005727907","display_name":"Jianmin Jiang","orcid":"https://orcid.org/0000-0002-7576-3999"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Jiang","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100407860"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":1.6422,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83834963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"11164","last_page":"11175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T12290","display_name":"Human Motion and Animation","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9955000281333923,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.8150421977043152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6214311718940735},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5214375853538513},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46693676710128784},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36246174573898315},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34184014797210693},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11837917566299438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8150421977043152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6214311718940735},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5214375853538513},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46693676710128784},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36246174573898315},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34184014797210693},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11837917566299438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3443670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3443670","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2239077016","display_name":null,"funder_award_id":"62376162","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5281037491","display_name":null,"funder_award_id":"62371310","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5958250743","display_name":null,"funder_award_id":"62032015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7492046624","display_name":null,"funder_award_id":"24JCXK03","funder_id":"https://openalex.org/F4320325571","funder_display_name":"Shenzhen University"},{"id":"https://openalex.org/G7771545035","display_name":null,"funder_award_id":"2023A1515011236","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320325571","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W318792885","https://openalex.org/W2133324800","https://openalex.org/W2579549467","https://openalex.org/W2606831796","https://openalex.org/W2740962769","https://openalex.org/W2962785943","https://openalex.org/W2963980128","https://openalex.org/W2981422075","https://openalex.org/W3012984147","https://openalex.org/W3034910302","https://openalex.org/W3035154952","https://openalex.org/W3107521863","https://openalex.org/W3109771530","https://openalex.org/W3173271937","https://openalex.org/W3183042936","https://openalex.org/W3184370138","https://openalex.org/W3195129957","https://openalex.org/W3198299822","https://openalex.org/W3201890160","https://openalex.org/W3206171352","https://openalex.org/W4213352847","https://openalex.org/W4214879921","https://openalex.org/W4226054716","https://openalex.org/W4226376247","https://openalex.org/W4285287023","https://openalex.org/W4304092470","https://openalex.org/W4312385518","https://openalex.org/W4312492610","https://openalex.org/W4312960102","https://openalex.org/W4317796337","https://openalex.org/W4353007189","https://openalex.org/W4377235251","https://openalex.org/W4379619455","https://openalex.org/W4385245566","https://openalex.org/W4386076183","https://openalex.org/W4386083046","https://openalex.org/W4388117494","https://openalex.org/W4389169596","https://openalex.org/W4389319239","https://openalex.org/W4392543796","https://openalex.org/W4393149385","https://openalex.org/W6675392924","https://openalex.org/W6761783306","https://openalex.org/W6763422710","https://openalex.org/W6791353385","https://openalex.org/W6804131122"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"Learning":[0],"to":[1,49,81,125,152,217],"build":[2],"3D":[3,19,60,101,112,122,138,155,222],"scene":[4,20,61,219],"graphs":[5,220],"is":[6,44,150],"essential":[7],"for":[8,175,182],"real-world":[9],"perception":[10],"in":[11],"a":[12,25,32,58,145],"structured":[13],"and":[14,30,41,47,87,100,104,111,131,141,177,193,199],"rich":[15],"fashion.":[16],"However,":[17],"previous":[18],"graph":[21,62,214],"generation":[22,63],"methods":[23],"utilize":[24],"fully":[26,235],"supervised":[27,236],"learning":[28],"manner":[29],"require":[31],"large":[33],"amount":[34],"of":[35,39,76,137,162,197,221],"entity-level":[36],"annotation":[37,242],"data":[38,241],"objects":[40,163,176,198],"relations,":[42],"which":[43],"extremely":[45],"resource-consuming":[46],"tedious":[48],"obtain.":[50],"To":[51],"tackle":[52],"this":[53],"problem,":[54],"we":[55,116,208],"propose":[56],"3D-VLAP,":[57],"weakly-supervised":[59],"method":[64],"via":[65,128],"Visual-Linguistic":[66],"Assisted":[67],"Pseudo-labeling.":[68],"Specifically,":[69],"our":[70,228],"3D-VLAP":[71,183,229],"exploits":[72],"the":[73,83,93,118,158,188,203,240],"superior":[74],"ability":[75],"current":[77,234],"large-scale":[78,146],"visual-linguistic":[79,148,204],"models":[80],"align":[82,154],"semantics":[84],"between":[85,97,109,190],"texts":[86,110],"2D":[88,98,126,142,166],"images,":[89],"as":[90,92],"well":[91],"naturally":[94],"existing":[95],"correspondences":[96,108],"images":[99,127,167],"point":[102,113,123,139,223],"clouds,":[103],"thus":[105],"implicitly":[106],"constructs":[107],"clouds.":[114,224],"First,":[115],"establish":[117],"positional":[119],"correspondence":[120],"from":[121],"clouds":[124,140],"camera":[129],"intrinsic":[130],"extrinsic":[132],"parameters,":[133],"thereby":[134],"achieving":[135],"alignment":[136],"images.":[143],"Subsequently,":[144],"cross-modal":[147],"model":[149,184],"employed":[151],"indirectly":[153],"instances":[156],"with":[157,168,233],"textual":[159,194],"category":[160,170,195],"labels":[161,174],"by":[164,186,202],"matching":[165],"object":[169],"labels.":[171],"The":[172],"pseudo":[173],"relations":[178,200],"are":[179],"then":[180],"produced":[181],"training":[185],"calculating":[187],"similarity":[189],"visual":[191],"embeddings":[192,196],"encoded":[201],"model,":[205],"respectively.":[206],"Ultimately,":[207],"design":[209],"an":[210],"edge":[211],"self-attention":[212],"based":[213],"neural":[215],"network":[216],"generate":[218],"Experiments":[225],"demonstrate":[226],"that":[227],"achieves":[230],"comparable":[231],"results":[232],"methods,":[237],"meanwhile":[238],"alleviating":[239],"pressure.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}