{"id":"https://openalex.org/W4405354885","doi":"https://doi.org/10.1007/s11263-026-02879-z","title":"Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations?","display_name":"Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations?","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W4405354885","doi":"https://doi.org/10.1007/s11263-026-02879-z"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-026-02879-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02879-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02879-z.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02879-z.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100376922","display_name":"Yifan Zhang","orcid":"https://orcid.org/0000-0001-7650-1109"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yifan Zhang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China","School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031957432","display_name":"Junhui Hou","orcid":"https://orcid.org/0000-0003-3431-2021"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Junhui Hou","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-3431-2021","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031957432"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":{"value":3690,"currency":"USD","value_usd":3690},"apc_paid":{"value":3690,"currency":"USD","value_usd":3690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00515648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.722000002861023,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.722000002861023,"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":0.6723999977111816,"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"}},{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.6466000080108643,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"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/distillation","display_name":"Distillation","score":0.5931175351142883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48338380455970764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.430225670337677},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40101322531700134},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3431626558303833},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1822921335697174},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.12297329306602478}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5931175351142883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48338380455970764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.430225670337677},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40101322531700134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3431626558303833},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1822921335697174},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.12297329306602478}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s11263-026-02879-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02879-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02879-z.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/d81be582-0914-46bc-9187-8bf4ac46365e","is_oa":true,"landing_page_url":"https://scholars.cityu.edu.hk/en/publications/d81be582-0914-46bc-9187-8bf4ac46365e","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Zhang, Y & Hou, J 2026, 'Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations?', International Journal of Computer Vision, vol. 134, no. 6, 271. https://doi.org/10.1007/s11263-026-02879-z","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arXiv.org:2412.08973","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.08973","pdf_url":"https://arxiv.org/pdf/2412.08973","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.08973","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.08973","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1007/s11263-026-02879-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02879-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02879-z.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G203989630","display_name":"Empowering Deep Modeling of 3D Point Clouds with 2D Visual Modalities","funder_award_id":"11219324","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"},{"id":"https://openalex.org/G3385717435","display_name":null,"funder_award_id":"11219324","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4278621838","display_name":null,"funder_award_id":"62422118","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6253342894","display_name":null,"funder_award_id":"11219422","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6881223726","display_name":null,"funder_award_id":"62422118","funder_id":"https://openalex.org/F4320335581","funder_display_name":"Young Scientists Fund"}],"funders":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405354885.pdf","grobid_xml":"https://content.openalex.org/works/W4405354885.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Abstract":[0],"Cross-modal":[1],"contrastive":[2,44,147],"distillation":[3,148],"has":[4],"recently":[5],"been":[6],"explored":[7],"for":[8,46],"learning":[9,49,94],"effective":[10],"3D":[11,47,126],"representations.":[12,33],"However,":[13],"existing":[14,145],"methods":[15,45,70,149],"focus":[16],"primarily":[17],"on":[18],"modality-shared":[19,75],"features,":[20],"neglecting":[21],"the":[22,26,40,91,136],"modality-specific":[23,77,97],"features":[24],"during":[25],"pre-training":[27],"process,":[28],"which":[29],"leads":[30],"to":[31,61,89,123],"suboptimal":[32],"In":[34],"this":[35],"paper,":[36],"we":[37,80,100,117],"theoretically":[38],"analyze":[39],"limitations":[41],"of":[42],"current":[43],"representation":[48,127],"and":[50,76,85,142],"propose":[51,118],"a":[52,102],"new":[53],"framework,":[54],"namely":[55],"CMCR":[56],"(Cross-Modal":[57],"Comprehensive":[58],"Representation":[59],"Learning),":[60],"address":[62],"these":[63],"shortcomings.":[64],"Our":[65],"approach":[66],"improves":[67],"upon":[68],"traditional":[69,140],"by":[71,139],"better":[72],"integrating":[73],"both":[74],"features.":[78,98],"Specifically,":[79],"introduce":[81,101],"masked":[82,120],"image":[83,121],"modeling":[84,122],"occupancy":[86],"estimation":[87],"tasks":[88],"guide":[90],"network":[92],"in":[93,150],"more":[95],"comprehensive":[96],"Furthermore,":[99],"novel":[103],"multi-modal":[104],"unified":[105],"codebook":[106],"that":[107,132],"learns":[108],"an":[109],"embedding":[110],"space":[111],"shared":[112],"across":[113],"different":[114],"modalities.":[115],"Besides,":[116],"geometry-enhanced":[119],"further":[124],"boost":[125],"learning.":[128],"Extensive":[129],"experiments":[130],"demonstrate":[131],"our":[133],"method":[134],"mitigates":[135],"challenges":[137],"faced":[138],"approaches":[141],"consistently":[143],"outperforms":[144],"image-to-LiDAR":[146],"downstream":[151],"tasks.":[152],"Code":[153],"will":[154],"be":[155],"available":[156],"at":[157],"https://github.com/Eaphan/CMCR":[158],".":[159]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}