{"id":"https://openalex.org/W4405902044","doi":"https://doi.org/10.1109/iccv51701.2025.00444","title":"CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting","display_name":"CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405902044","doi":"https://doi.org/10.1109/iccv51701.2025.00444"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.19142","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049196219","display_name":"Siyu Jiao","orcid":"https://orcid.org/0000-0002-0795-8401"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Jiao","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021859952","display_name":"Haoye Dong","orcid":"https://orcid.org/0000-0001-8169-8890"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haoye Dong","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101595849","display_name":"Yuyang Yin","orcid":"https://orcid.org/0009-0005-7443-6194"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyang Yin","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075329194","display_name":"Zequn Jie","orcid":"https://orcid.org/0000-0002-3038-5891"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zequn Jie","raw_affiliation_strings":["Meituan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038795686","display_name":"Yinlong Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinlong Qian","raw_affiliation_strings":["Meituan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362745","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0002-8581-9554"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002072267","display_name":"Humphrey Shi","orcid":"https://orcid.org/0000-0002-2922-5663"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Humphrey Shi","raw_affiliation_strings":["Georgia Institute of Technology,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087043856","display_name":"Yunchao Wei","orcid":"https://orcid.org/0000-0002-2812-8781"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunchao Wei","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University,China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4670","last_page":"4680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9940000176429749,"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":0.9940000176429749,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9932000041007996,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9632999897003174,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.6173743009567261},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.588286817073822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.419948548078537},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41476181149482727},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08752572536468506},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.07730028033256531}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6173743009567261},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.588286817073822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.419948548078537},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41476181149482727},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08752572536468506},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.07730028033256531},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.19142","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.19142","pdf_url":"https://arxiv.org/pdf/2412.19142","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.19142","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.19142","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.19142","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.19142","pdf_url":"https://arxiv.org/pdf/2412.19142","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1629255802","display_name":null,"funder_award_id":"U24B20179","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3306742896","display_name":null,"funder_award_id":"92470203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4316271325","display_name":null,"funder_award_id":"2024XKRC082","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8655215462","display_name":null,"funder_award_id":"L242022","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"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},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recent":[0],"works":[1],"in":[2,47,76,103,151],"3D":[3,12,26,29,44,59,171],"multimodal":[4,13,60,71,154,159,174],"learning":[5,73,152],"have":[6],"made":[7],"remarkable":[8],"progress.":[9],"However,":[10],"typically":[11],"models":[14,168],"are":[15,89],"only":[16],"capable":[17],"of":[18,43,56,117,132,144],"handling":[19],"point":[20,36,57,99,166],"clouds.":[21],"Compared":[22],"to":[23,83,126,141],"the":[24,33,40,54,80,104,114,128,157],"emerging":[25],"representation":[27,61,72],"technique,":[28],"Gaussian":[30],"Splatting":[31],"(3DGS),":[32],"spatially":[34],"sparse":[35],"cloud":[37,100],"cannot":[38],"depict":[39],"texture":[41],"information":[42],"objects,":[45],"resulting":[46,102],"inferior":[48],"reconstruction":[49],"capabilities.":[50],"This":[51],"limitation":[52],"constrains":[53],"potential":[55],"cloud-based":[58,167],"learning.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,120,136],"present":[67],"CLIP-GS,":[68],"a":[69],"novel":[70],"framework":[74],"grounded":[75],"3DGS.":[77],"We":[78],"introduce":[79,121],"GS":[81],"Tokenizer":[82],"generate":[84,142],"serialized":[85],"gaussian":[86],"tokens,":[87],"which":[88],"then":[90],"processed":[91],"through":[92],"transformer":[93],"layers":[94],"pre-initialized":[95],"with":[96],"weights":[97],"from":[98],"models,":[101],"3DGS":[105,112],"embeddings.":[106],"CLIP-GS":[107,150,161],"leverages":[108],"contrastive":[109],"loss":[110,125],"between":[111],"and":[113,119,130,147,164,177],"visual-text":[115],"embeddings":[116],"CLIP,":[118],"an":[122,138],"image":[123],"voting":[124],"guide":[127],"directionality":[129],"convergence":[131],"gradient":[133],"optimization.":[134],"Furthermore,":[135],"develop":[137],"efficient":[139],"way":[140],"triplets":[143],"3DGS,":[145],"images,":[146],"text,":[148],"facilitating":[149],"unified":[153],"representations.":[155],"Leveraging":[156],"well-aligned":[158],"representations,":[160],"demonstrates":[162],"versatility":[163],"outperforms":[165],"on":[169],"various":[170],"tasks,":[172],"including":[173],"retrieval,":[175],"zero-shot,":[176],"few-shot":[178],"classification.":[179]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2024-12-31T00:00:00"}