{"id":"https://openalex.org/W4415536638","doi":"https://doi.org/10.1145/3746027.3758145","title":"Align 3D Representation and Text Embedding for 3D Content Personalization","display_name":"Align 3D Representation and Text Embedding for 3D Content Personalization","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536638","doi":"https://doi.org/10.1145/3746027.3758145"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3758145","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758145","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758145","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qi Song","orcid":"https://orcid.org/0009-0006-7896-1567"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qi Song","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0006-7896-1567","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018169096","display_name":"Ziyuan Luo","orcid":"https://orcid.org/0000-0003-1580-9809"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ziyuan Luo","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-1580-9809","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084054549","display_name":"Ka Chun Cheung","orcid":"https://orcid.org/0000-0002-2939-4686"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ka Chun Cheung","raw_affiliation_strings":["NVIDIA AI Technology Center, NVIDIA, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-2939-4686","affiliations":[{"raw_affiliation_string":"NVIDIA AI Technology Center, NVIDIA, Hong Kong SAR, China","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077539496","display_name":"Simon See","orcid":"https://orcid.org/0000-0002-4958-9237"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon See","raw_affiliation_strings":["NVIDIA AI Technology Center, NVIDIA, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4958-9237","affiliations":[{"raw_affiliation_string":"NVIDIA AI Technology Center, NVIDIA, Singapore, Singapore","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085201191","display_name":"Renjie Wan","orcid":"https://orcid.org/0000-0002-0161-0367"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Renjie Wan","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-0161-0367","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2585572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12199","last_page":"12208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9922000169754028,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9922000169754028,"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/T12290","display_name":"Human Motion and Animation","score":0.9894000291824341,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9890999794006348,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.8695999979972839},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7530999779701233},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5541999936103821},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.47290000319480896},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.4318000078201294},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42899999022483826}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.8695999979972839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570000290870667},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7530999779701233},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5541999936103821},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40369999408721924},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3880999982357025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37389999628067017},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2754000127315521}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3758145","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758145","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.16932","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.16932","pdf_url":"https://arxiv.org/pdf/2508.16932","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3746027.3758145","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758145","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2945022816","display_name":null,"funder_award_id":"62302415","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1997057955","https://openalex.org/W3109585842","https://openalex.org/W3215769467","https://openalex.org/W4285191490","https://openalex.org/W4312497550","https://openalex.org/W4312839164","https://openalex.org/W4312846625","https://openalex.org/W4312933868","https://openalex.org/W4385318467","https://openalex.org/W4385527149","https://openalex.org/W4386065887","https://openalex.org/W4386076532","https://openalex.org/W4386148430","https://openalex.org/W4390871705","https://openalex.org/W4390872653","https://openalex.org/W4390873054","https://openalex.org/W4390873331","https://openalex.org/W4401029143","https://openalex.org/W4402715988","https://openalex.org/W4402727915","https://openalex.org/W4402733585","https://openalex.org/W4402753761"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"NeRF":[3],"and":[4,11,82,105,134],"3DGS":[5],"have":[6],"significantly":[7],"enhanced":[8],"the":[9,75,144],"efficiency":[10],"quality":[12],"of":[13,20,88,136,158],"3D":[14,22,29,56,80,92,103,119,123,137,159],"content":[15,23,57,81,138],"synthesis.":[16],"However,":[17,74],"efficient":[18,132],"personalization":[19,30,68,135,157],"generated":[21],"remains":[24],"a":[25,51,112,122],"critical":[26],"challenge.":[27],"Current":[28],"approaches":[31],"predominantly":[32],"rely":[33],"on":[34],"knowledge":[35],"distillation-based":[36],"methods,":[37],"which":[38],"require":[39],"computationally":[40,147],"expensive":[41],"retraining":[42,148],"procedures.":[43,149],"To":[44],"address":[45],"this":[46,97],"challenge,":[47],"we":[48,110],"propose":[49],"Invert3D,":[50],"novel":[52],"framework":[53],"for":[54,146],"convenient":[55],"personalization.":[58,93],"Nowadays,":[59],"vision-language":[60],"models":[61],"such":[62],"as":[63],"CLIP":[64],"enable":[65],"direct":[66,86],"image":[67],"through":[69,139],"aligned":[70,125],"vision-text":[71],"embedding":[72,107,124],"spaces.":[73,108],"inherent":[76],"structural":[77],"differences":[78],"between":[79,102],"2D":[83],"images":[84],"preclude":[85],"application":[87],"these":[89],"techniques":[90],"to":[91],"Our":[94],"approach":[95],"bridges":[96],"gap":[98],"by":[99],"establishing":[100],"alignment":[101,130],"representations":[104],"text":[106,127],"Specifically,":[109],"develop":[111],"camera-conditioned":[113],"3D-to-text":[114],"inverse":[115],"mechanism":[116],"that":[117,153],"projects":[118],"contents":[120],"into":[121],"with":[126],"embeddings.":[128],"This":[129],"enables":[131],"manipulation":[133],"natural":[140],"language":[141],"prompts,":[142],"eliminating":[143],"need":[145],"Extensive":[150],"experiments":[151],"demonstrate":[152],"Invert3D":[154],"achieves":[155],"effective":[156],"content.":[160]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}