{"id":"https://openalex.org/W4413155814","doi":"https://doi.org/10.1109/cvpr52734.2025.00407","title":"SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models","display_name":"SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413155814","doi":"https://doi.org/10.1109/cvpr52734.2025.00407"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5066227950","display_name":"Kevin Miller","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Miller","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030038191","display_name":"Aditya Gangrade","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditya Gangrade","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102893907","display_name":"Samarth Mishra","orcid":"https://orcid.org/0000-0003-3425-2647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samarth Mishra","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075906727","display_name":"Kate Saenko","orcid":"https://orcid.org/0000-0002-7564-7218"},"institutions":[{"id":"https://openalex.org/I81844223","display_name":"Fairchild Semiconductor (United States)","ror":"https://ror.org/03yca1933","country_code":"US","type":"company","lineage":["https://openalex.org/I81844223"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kate Saenko","raw_affiliation_strings":["Boston University and Meta AI (FAIR)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University and Meta AI (FAIR)","institution_ids":["https://openalex.org/I81844223"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048704387","display_name":"Venkatesh Saligrama","orcid":"https://orcid.org/0000-0002-0675-2268"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Venkatesh Saligrama","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4313","last_page":"4321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9473999738693237,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9473999738693237,"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/computer-science","display_name":"Computer science","score":0.6820879578590393},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6238417625427246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5956614017486572},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.52829909324646},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49803924560546875},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4390571713447571},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43493491411209106},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41735637187957764},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06668388843536377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6820879578590393},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6238417625427246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5956614017486572},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.52829909324646},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49803924560546875},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4390571713447571},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43493491411209106},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41735637187957764},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06668388843536377},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2007972815","https://openalex.org/W2031489346","https://openalex.org/W4386113259","https://openalex.org/W4387969338","https://openalex.org/W4390203943","https://openalex.org/W4390871773","https://openalex.org/W4390872508","https://openalex.org/W4390873546","https://openalex.org/W4393149364","https://openalex.org/W4401024541","https://openalex.org/W4402963229","https://openalex.org/W4404967481"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W4411535265","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966"],"abstract_inverted_index":{"Zero-shot":[0],"multi-label":[1],"recognition":[2],"(MLR)":[3],"with":[4],"Vision-Language":[5],"Models":[6],"(VLMs)":[7],"faces":[8],"significant":[9],"challenges":[10],"without":[11,43],"training":[12,44,140],"data,":[13,141],"model":[14],"tuning,":[15],"or":[16,24,46],"architectural":[17,25],"modifications.":[18],"Existing":[19],"approaches":[20],"require":[21],"prompt":[22],"tuning":[23],"adaptations,":[26],"limiting":[27],"zero-shot":[28,123,149],"applicability.":[29],"Our":[30,90,119],"work":[31],"proposes":[32],"a":[33],"novel":[34],"solution":[35],"treating":[36],"VLMs":[37],"as":[38],"black":[39],"boxes,":[40],"leveraging":[41],"scores":[42,58,100],"data":[45],"ground":[47],"truth.":[48],"We":[49,109],"make":[50],"two":[51],"contributions.":[52],"First,":[53],"we":[54,81],"find":[55],"that":[56,66,96],"VLM":[57],"suffer":[59],"from":[60],"image-":[61],"and":[62,65,75],"prompt-specific":[63],"biases,":[64],"simple":[67],"standardization":[68],"is":[69],"surprisingly":[70,103],"effective":[71],"at":[72,155],"removing":[73],"these":[74],"boosting":[76],"MLR":[77],"performance.":[78],"And":[79],"second,":[80],"introduce":[82,110],"compound":[83,99],"prompts":[84],"grounded":[85],"in":[86],"realistic":[87],"object":[88,145],"combinations.":[89],"analysis":[91],"reveals":[92],"\"AND\"/\"OR\"":[93],"signal":[94],"ambiguities":[95],"cause":[97],"maximum":[98],"to":[101,106,115,137],"be":[102,153],"suboptimal":[104],"compared":[105,136],"second-highest":[107],"scores.":[108],"an":[111],"adaptive":[112],"fusion":[113],"method":[114,120],"address":[116],"this":[117],"issue.":[118],"enhances":[121],"other":[122],"approaches,":[124],"consistently":[125],"improving":[126],"their":[127],"results.":[128],"Experiments":[129],"show":[130],"superior":[131],"mean":[132],"Average":[133],"Precision":[134],"(mAP)":[135],"methods":[138],"requiring":[139],"achieved":[142],"through":[143],"refined":[144],"ranking":[146],"for":[147],"robust":[148],"MLR.":[150],"Code":[151],"can":[152],"found":[154],"https://github.com/kjmillerCURIS/SPARC.":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}