{"id":"https://openalex.org/W4415157805","doi":"https://doi.org/10.1109/3dv69130.2026.00168","title":"3D CoCa: Contrastive Learners are 3D Captioners","display_name":"3D CoCa: Contrastive Learners are 3D Captioners","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W4415157805","doi":"https://doi.org/10.1109/3dv69130.2026.00168"},"language":"en","primary_location":{"id":"doi:10.1109/3dv69130.2026.00168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.09518","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101927760","display_name":"Ting Huang","orcid":"https://orcid.org/0000-0001-9450-6229"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Huang","raw_affiliation_strings":["School of Computer Science, Peking University,State Key Laboratory of Multimedia Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,State Key Laboratory of Multimedia Information Processing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107048167","display_name":"Zeyu Zhang","orcid":"https://orcid.org/0009-0004-4517-0617"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zeyu Zhang","raw_affiliation_strings":["The Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055023660","display_name":"Yemin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yemin Wang","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100703188","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0003-3961-8871"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["School of Computer Science, Peking University,State Key Laboratory of Multimedia Information Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,State Key Laboratory of Multimedia Information Processing","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.00453837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1771","last_page":"1780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.41819998621940613,"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"}},"topics":[{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.41819998621940613,"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/closed-captioning","display_name":"Closed captioning","score":0.6718999743461609},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5317000150680542},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5271999835968018},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5189999938011169},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49230000376701355},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.413100004196167},{"id":"https://openalex.org/keywords/coca","display_name":"Coca","score":0.4081000089645386},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.4077000021934509},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4072999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8222000002861023},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6718999743461609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6049000024795532},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.539900004863739},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49230000376701355},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.413100004196167},{"id":"https://openalex.org/C2781313679","wikidata":"https://www.wikidata.org/wiki/Q66793593","display_name":"Coca","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3345000147819519},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2615000009536743}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/3dv69130.2026.00168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.09518","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.09518","pdf_url":"https://arxiv.org/pdf/2504.09518","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"},{"id":"doi:10.48550/arxiv.2504.09518","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.09518","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.09518","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.09518","pdf_url":"https://arxiv.org/pdf/2504.09518","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"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,9,38,51,72,98,134,148],"captioning,":[1],"which":[2],"aims":[3],"to":[4,18,65,75,83],"describe":[5],"the":[6,19,88,112,141],"content":[7],"of":[8,22],"scenes":[10],"in":[11,29,106,158],"natural":[12],"language,":[13],"remains":[14],"highly":[15],"challenging":[16],"due":[17],"inherent":[20],"sparsity":[21],"point":[23],"clouds":[24],"and":[25,79,103,128,135,143,156],"weak":[26],"cross-modal":[27],"alignment":[28],"existing":[30],"methods.":[31],"To":[32],"address":[33],"these":[34],"challenges,":[35],"we":[36],"propose":[37],"CoCa,":[39],"a":[40,55,60,70,80,107],"novel":[41],"unified":[42],"framework":[43],"that":[44,92,147],"seamlessly":[45],"combines":[46],"contrastive":[47,102],"vision-language":[48,63],"learning":[49],"with":[50],"caption":[52],"generation":[53],"into":[54],"single":[56],"architecture.":[57],"We":[58],"design":[59],"frozen":[61],"CLIP":[62],"backbone":[64],"provide":[66],"rich":[67],"semantic":[68,130],"priors,":[69],"spatially-aware":[71],"scene":[73],"encoder":[74],"capture":[76],"geometric":[77],"context,":[78],"multi-modal":[81],"decoder":[82],"generate":[84],"descriptive":[85],"captions.":[86],"Unlike":[87],"prior":[89],"two-stage":[90],"methods":[91],"rely":[93],"on":[94,140],"explicit":[95],"object":[96],"proposals,":[97],"CoCa":[99,149],"jointly":[100],"optimizes":[101],"captioning":[104],"objectives":[105],"shared":[108],"feature":[109],"space,":[110],"eliminating":[111],"need":[113],"for":[114],"external":[115],"detectors":[116],"or":[117],"handcrafted":[118],"proposals.":[119],"This":[120],"joint":[121],"training":[122],"paradigm":[123],"yields":[124],"stronger":[125],"spatial":[126],"reasoning":[127],"richer":[129],"grounding":[131],"by":[132,154],"aligning":[133],"textual":[136],"representations.":[137],"Extensive":[138],"experiments":[139],"ScanRefer":[142],"Nr3D":[144],"benchmarks":[145],"demonstrate":[146],"significantly":[150],"outperforms":[151],"current":[152],"state-of-the-arts":[153],"10.2%":[155],"5.76%":[157],"CIDEr@0.5IoU,":[159],"respectively.":[160],"Code":[161],"will":[162],"be":[163],"available":[164],"at":[165],"https://github.com/AIGeeksGroup/3DCoCa.":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-14T00:00:00"}