{"id":"https://openalex.org/W4283838088","doi":"https://doi.org/10.1145/3503161.3549201","title":"Can Language Understand Depth?","display_name":"Can Language Understand Depth?","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4283838088","doi":"https://doi.org/10.1145/3503161.3549201"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3549201","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3549201","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102891082","display_name":"Renrui Zhang","orcid":"https://orcid.org/0000-0003-4503-5277"},"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":"Renrui Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025410882","display_name":"Ziyao Zeng","orcid":"https://orcid.org/0009-0003-1803-7434"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyao Zeng","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114400807","display_name":"Ziyu Guo","orcid":"https://orcid.org/0000-0001-9606-9691"},"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":"Ziyu Guo","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027978516","display_name":"Yafeng Li","orcid":"https://orcid.org/0000-0003-2448-5092"},"institutions":[{"id":"https://openalex.org/I2799293361","display_name":"Baoji University of Arts and Sciences","ror":"https://ror.org/05nx0xs09","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799293361"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafeng Li","raw_affiliation_strings":["School of Computer, Baoji University of Arts and Science, Baoji, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Baoji University of Arts and Science, Baoji, China","institution_ids":["https://openalex.org/I2799293361"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6868","last_page":"6874"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9986000061035156,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9986000061035156,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9968000054359436,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9948999881744385,"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":0.8242116570472717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6436371207237244},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5720295310020447},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4620053470134735},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43690311908721924},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4223494529724121},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41357940435409546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242116570472717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6436371207237244},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5720295310020447},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4620053470134735},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43690311908721924},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4223494529724121},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41357940435409546},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3549201","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3549201","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W2115579991","https://openalex.org/W2166747022","https://openalex.org/W2194775991","https://openalex.org/W2520707372","https://openalex.org/W2963488291","https://openalex.org/W2963906250","https://openalex.org/W2986766740","https://openalex.org/W2990138404","https://openalex.org/W3035254347","https://openalex.org/W3096609285","https://openalex.org/W3118453581","https://openalex.org/W3135367836","https://openalex.org/W3138516171","https://openalex.org/W3215100485","https://openalex.org/W4312818263","https://openalex.org/W6684620982"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W200819717","https://openalex.org/W2032269556","https://openalex.org/W1991834176","https://openalex.org/W2944448661","https://openalex.org/W2064421702","https://openalex.org/W4253756925","https://openalex.org/W2805523177","https://openalex.org/W2131956013","https://openalex.org/W2036566443"],"abstract_inverted_index":{"Besides":[0],"image":[1,71],"classification,":[2],"Contrastive":[3],"Language-Image":[4],"Pre-training":[5],"(CLIP)":[6],"has":[7],"accomplished":[8],"extraordinary":[9],"success":[10],"for":[11,57,89],"a":[12,75,85,141],"wide":[13],"range":[14],"of":[15,39,69],"vision":[16],"tasks,":[17],"including":[18],"object-level":[19],"and":[20,80,101,129],"3D":[21],"space":[22],"understanding.":[23],"However,":[24],"it's":[25],"still":[26],"challenging":[27],"to":[28,54,74,84,116,125],"transfer":[29],"semantic":[30,77,122],"knowledge":[31,124],"learned":[32],"from":[33,120],"CLIP":[34,56],"into":[35],"more":[36],"intricate":[37],"tasks":[38,128],"quantified":[40,86,126],"targets,":[41],"such":[42],"as":[43],"depth":[44,60,87,133],"estimation":[45],"with":[46],"geometric":[47],"information.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,112],"propose":[53],"apply":[55],"zero-shot":[58,118,131],"monocular":[59,132],"estimation,":[61],"named":[62],"DepthCLIP.":[63],"We":[64,135],"found":[65],"that":[66],"the":[67,104,114,121,144],"patches":[68],"input":[70],"could":[72,139],"respond":[73],"certain":[76],"distance":[78],"token":[79],"then":[81],"be":[82],"projected":[83],"bin":[88],"coarse":[90],"estimation.":[91,134],"Without":[92],"any":[93],"training,":[94],"our":[95,109,137],"DepthCLIP":[96],"surpasses":[97],"existing":[98],"unsupervised":[99],"methods":[100],"even":[102],"approaches":[103],"early":[105],"fully-supervised":[106],"networks.":[107],"To":[108],"best":[110],"knowledge,":[111],"are":[113],"first":[115],"conduct":[117],"adaptation":[119],"language":[123],"downstream":[127],"perform":[130],"hope":[136],"work":[138],"cast":[140],"light":[142],"on":[143],"future":[145],"research.":[146],"The":[147],"code":[148],"is":[149],"available":[150],"at":[151],"https://github.com/Adonis-galaxy/DepthCLIP.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":16}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}