{"id":"https://openalex.org/W7094956897","doi":"https://doi.org/10.1145/3746027.3755465","title":"Multi-modal Prototype Guided Few-shot Object Detection","display_name":"Multi-modal Prototype Guided Few-shot Object Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W7094956897","doi":"https://doi.org/10.1145/3746027.3755465"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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":"Chenbo Zhang","orcid":"https://orcid.org/0000-0002-6773-598X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenbo Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bing Huangfu","orcid":"https://orcid.org/0009-0009-6213-872X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Huangfu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongxu Ma","orcid":"https://orcid.org/0009-0002-8623-0976"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxu Ma","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jihong Guan","orcid":"https://orcid.org/0000-0003-2313-7635"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihong Guan","raw_affiliation_strings":["Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shuigeng Zhou","orcid":"https://orcid.org/0000-0002-1949-2768"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuigeng Zhou","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76727527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1852","last_page":"1861"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.6362000107765198,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.6362000107765198,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.14640000462532043,"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":0.13989999890327454,"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/object-detection","display_name":"Object detection","score":0.6305000185966492},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5382000207901001},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45170000195503235},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4406999945640564},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4172999858856201},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4081000089645386},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4009000062942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7447999715805054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6593000292778015},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6305000185966492},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4172999858856201},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C2779542340","wikidata":"https://www.wikidata.org/wiki/Q1062461","display_name":"Learning object","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6432873010635376,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2079639858","https://openalex.org/W2108598243","https://openalex.org/W2962766617","https://openalex.org/W2963351448","https://openalex.org/W2983156430","https://openalex.org/W2997616671","https://openalex.org/W3034974675","https://openalex.org/W3096609285","https://openalex.org/W3166058839","https://openalex.org/W3169708801","https://openalex.org/W3180959016","https://openalex.org/W3194193742","https://openalex.org/W3207933943","https://openalex.org/W3215828051","https://openalex.org/W4214724741","https://openalex.org/W4303449801","https://openalex.org/W4304084306","https://openalex.org/W4312446817","https://openalex.org/W4312956471","https://openalex.org/W4382457177","https://openalex.org/W4386076362","https://openalex.org/W4390871681","https://openalex.org/W4390872318","https://openalex.org/W4392903013","https://openalex.org/W4393148213","https://openalex.org/W4393153493","https://openalex.org/W4402704540","https://openalex.org/W4402754181","https://openalex.org/W4403791693","https://openalex.org/W4406233699","https://openalex.org/W4408519749","https://openalex.org/W4408520873"],"related_works":[],"abstract_inverted_index":{"Few-shot":[0],"object":[1,156],"detection":[2,147,180],"(FSOD)":[3],"is":[4],"an":[5,107],"important":[6],"problem":[7],"in":[8,28,202],"computer":[9],"vision,":[10],"aiming":[11],"to":[12,46,87,113,168],"accurately":[13],"detect":[14],"objects":[15],"with":[16],"only":[17],"a":[18,123,160],"few":[19],"annotated":[20],"examples.":[21],"Prototype":[22],"learning":[23,167],"has":[24],"been":[25],"widely":[26],"explored":[27],"this":[29,92],"field.":[30],"Some":[31],"methods":[32],"extract":[33],"visual":[34,63,72,115,136],"prototypes":[35,52,75,85,118,129,139],"from":[36,68,119],"support":[37],"images,":[38],"but":[39],"the":[40,97,145,179],"limited":[41],"sample":[42],"size":[43],"often":[44],"leads":[45],"unrepresentative":[47],"features.":[48],"Others":[49],"use":[50],"textual":[51,74,117],"generated":[53],"by":[54,165],"pre-trained":[55],"vision-language":[56],"models":[57,121],"such":[58],"as":[59],"CLIP,":[60],"which":[61],"lack":[62],"detail":[64,80],"and":[65,73,81,116,135,158,194,209],"may":[66],"suffer":[67],"language":[69],"ambiguity.":[70],"As":[71],"offer":[76],"complementary":[77],"strengths":[78],"---":[79],"generalization":[82],"respectively,":[83],"single-modal":[84,188],"struggle":[86],"balance":[88],"both.":[89],"To":[90],"address":[91],"issue,":[93],"we":[94],"propose":[95],"MP-DETR,":[96],"first":[98],"multi-modal":[99,109,127,176],"prototype":[100,110,161],"guided":[101],"method":[102],"for":[103,149],"FSOD.":[104],"We":[105],"design":[106],"adaptive":[108],"fusion":[111],"module":[112],"combine":[114],"foundation":[120],"using":[122],"gating":[124],"mechanism,":[125],"producing":[126],"class":[128],"that":[130,197],"retain":[131],"both":[132],"general":[133],"semantics":[134],"specificity.":[137],"These":[138],"are":[140],"then":[141],"deeply":[142],"integrated":[143],"into":[144,178],"DETR":[146],"pipeline":[148],"guiding":[150],"potential":[151],"region":[152],"selection,":[153],"enhancing":[154],"corresponding":[155],"queries,":[157],"constructing":[159],"similarity-based":[162],"classifier":[163],"enhanced":[164],"contrastive":[166],"improve":[169],"discrimination":[170],"among":[171],"similar":[172],"classes.":[173],"By":[174],"incorporating":[175],"guidance":[177],"process,":[181],"MP-DETR":[182,198],"achieves":[183,199],"better":[184],"performance":[185],"than":[186],"existing":[187],"methods.":[189],"Extensive":[190],"experiments":[191],"on":[192],"MS-COCO":[193],"Pascal-VOC":[195],"show":[196],"SOTA":[200],"results":[201],"various":[203],"few-shot":[204],"settings,":[205],"confirming":[206],"its":[207],"effectiveness":[208],"superiority.":[210]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}