{"id":"https://openalex.org/W4403792419","doi":"https://doi.org/10.1145/3664647.3680885","title":"Selective Vision-Language Subspace Projection for Few-shot CLIP","display_name":"Selective Vision-Language Subspace Projection for Few-shot CLIP","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792419","doi":"https://doi.org/10.1145/3664647.3680885"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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":null,"display_name":"Xingyu Zhu","orcid":"https://orcid.org/0000-0001-5225-7770"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Zhu","raw_affiliation_strings":["University of Science and Technology of China, Hefei City, Anhui Province, China"],"raw_orcid":"https://orcid.org/0000-0001-5225-7770","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei City, Anhui Province, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009738035","display_name":"Beier Zhu","orcid":"https://orcid.org/0000-0002-7900-6979"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Beier Zhu","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7900-6979","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040998859","display_name":"Yi Tan","orcid":"https://orcid.org/0000-0002-8670-1312"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Tan","raw_affiliation_strings":["University of Science and Technology of China, Hefei City, China"],"raw_orcid":"https://orcid.org/0000-0002-8670-1312","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei City, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400159","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0002-4881-9344"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei City, China"],"raw_orcid":"https://orcid.org/0000-0002-4881-9344","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei City, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043525989","display_name":"Yanbin Hao","orcid":"https://orcid.org/0000-0002-0695-1566"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbin Hao","raw_affiliation_strings":["University of Science and Technology of China, Hefei City, China"],"raw_orcid":"https://orcid.org/0000-0002-0695-1566","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei City, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7374-8739","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3848","last_page":"3857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983000159263611,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9878000020980835,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7342522144317627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.689879834651947},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.6599785089492798},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.6363643407821655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5857357978820801},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5724380016326904},{"id":"https://openalex.org/keywords/oblique-projection","display_name":"Oblique projection","score":0.4530203342437744},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.43615058064460754},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3746829926967621},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.1943034529685974},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11526894569396973},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09113174676895142}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7342522144317627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.689879834651947},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6599785089492798},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.6363643407821655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5857357978820801},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5724380016326904},{"id":"https://openalex.org/C161666082","wikidata":"https://www.wikidata.org/wiki/Q14551923","display_name":"Oblique projection","level":3,"score":0.4530203342437744},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.43615058064460754},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3746829926967621},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.1943034529685974},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11526894569396973},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09113174676895142},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2160021383","https://openalex.org/W2533598788","https://openalex.org/W2896487916","https://openalex.org/W2964194231","https://openalex.org/W2965778995","https://openalex.org/W3037492894","https://openalex.org/W3096719817","https://openalex.org/W3097667724","https://openalex.org/W4239072543","https://openalex.org/W4304014785","https://openalex.org/W4312818263","https://openalex.org/W4312933868","https://openalex.org/W4313175608","https://openalex.org/W4360993849","https://openalex.org/W4382240281","https://openalex.org/W4386071542","https://openalex.org/W4386075788","https://openalex.org/W4390873530","https://openalex.org/W4390873714","https://openalex.org/W4400228564","https://openalex.org/W4401929513"],"related_works":["https://openalex.org/W3092280629","https://openalex.org/W2033523051","https://openalex.org/W2320608497","https://openalex.org/W2510419178","https://openalex.org/W2497720472","https://openalex.org/W2248642921","https://openalex.org/W2373703221","https://openalex.org/W2377235230","https://openalex.org/W4292659306","https://openalex.org/W1637798125"],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"such":[2],"as":[3,44,83],"CLIP":[4],"are":[5],"capable":[6],"of":[7,25],"mapping":[8],"the":[9,23,45,88,116,125,169],"different":[10],"modality":[11,35],"data":[12],"into":[13,130,150],"a":[14,67,84,101,105],"unified":[15],"feature":[16],"space,":[17],"enabling":[18],"zero/few-shot":[19],"inference":[20],"by":[21],"measuring":[22],"similarity":[24],"given":[26],"images":[27],"and":[28,47,80,104,121,127,145],"texts.":[29],"However,":[30],"most":[31],"existing":[32],"methods":[33],"overlook":[34],"gaps":[36],"in":[37,57],"CLIP's":[38],"encoded":[39],"features,":[40],"which":[41,75],"is":[42,175],"shown":[43],"text":[46,128],"image":[48,78,112,120,126],"features":[49,79,113,129],"lie":[50],"far":[51],"apart":[52],"from":[53],"each":[54],"other,":[55],"resulting":[56],"limited":[58],"classification":[59],"performance.":[60],"To":[61],"tackle":[62],"this":[63],"issue,":[64],"we":[65],"introduce":[66],"method":[68],"called":[69],"Selective":[70],"Vision-Language":[71],"Subspace":[72],"Projection":[73],"(SSP),":[74],"incorporates":[76],"local":[77,111],"utilizes":[81],"them":[82],"bridge":[85],"to":[86,114,134],"enhance":[87],"alignment":[89,166,171],"between":[90],"image-text":[91],"pairs.":[92],"Specifically,":[93],"our":[94,138],"SSP":[95],"framework":[96],"comprises":[97],"two":[98],"parallel":[99],"modules:":[100],"vision":[102],"projector":[103],"language":[106],"projector.":[107],"Both":[108],"projectors":[109],"utilize":[110],"span":[115],"respective":[117,132],"subspaces":[118,133],"for":[119],"texts,":[122],"thereby":[123],"projecting":[124],"their":[131],"achieve":[135],"alignment.":[136],"Moreover,":[137],"approach":[139],"entails":[140],"only":[141],"training-free":[142],"matrix":[143],"calculations":[144],"can":[146],"be":[147],"seamlessly":[148],"integrated":[149],"advanced":[151],"CLIP-based":[152],"few-shot":[153],"learning":[154],"frameworks.":[155],"Extensive":[156],"experiments":[157],"on":[158],"11":[159],"datasets":[160],"have":[161],"demonstrated":[162],"SSP's":[163],"superior":[164],"text-image":[165],"capabilities,":[167],"outperforming":[168],"state-of-the-art":[170],"methods.":[172],"The":[173],"code":[174],"available":[176],"at":[177],"https://github.com/zhuhsingyuu/SSP":[178]},"counts_by_year":[{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
